From 59c980e495e5a8e459d00ea0abba99147926446c Mon Sep 17 00:00:00 2001 From: Dominik Roth Date: Tue, 23 Jan 2024 17:42:13 +0100 Subject: [PATCH] Final? touches to the docs --- docs/build/doctrees/environment.pickle | Bin 56764 -> 56764 bytes .../doctrees/envs/fancy/airhockey.doctree | Bin 8182 -> 8639 bytes docs/build/doctrees/envs/fancy/mujoco.doctree | Bin 66269 -> 66003 bytes docs/build/doctrees/index.doctree | Bin 22319 -> 22319 bytes .../_sources/envs/fancy/airhockey.rst.txt | 2 +- .../html/_sources/envs/fancy/mujoco.md.txt | 4 ++-- docs/build/html/_sources/index.rst.txt | 2 +- docs/build/html/envs/fancy/airhockey.html | 2 +- docs/build/html/envs/fancy/mujoco.html | 4 ++-- docs/build/html/index.html | 2 +- docs/build/html/searchindex.js | 2 +- docs/source/envs/fancy/airhockey.rst | 2 +- docs/source/envs/fancy/mujoco.md | 4 ++-- 13 files changed, 12 insertions(+), 12 deletions(-) diff --git a/docs/build/doctrees/environment.pickle b/docs/build/doctrees/environment.pickle index 403c826cb69f33eabee0b5e012e261c3928c2edc..43e6647435b75f1d0a866701ef82e06a5226ed48 100644 GIT binary patch delta 3416 zcmZ8k3s6+&73KnwGJ`~5E1&^{y(R*>yp(4~Q82EeytFkYL0ERzb$@pEt}LiT>Z%d& zl2upFHNzx6s(DS-i8Qy(G@5D6jNML?Y1;7>L1Hw%5+liUCTTjxPJ7OO|Uo& zvN^4-oi1oHiuo}XFCLJ@&s%5lSbGZG-AuAdN?^+WY1(NE#Pp6S`o<2s$KGjiDFK7F zbGO&gX|Xvyj#hdQ_tfNeiw{rh_E{WuB@oZ|q&Stp&$x}@DS>3o)#>qdSzInlms9d6 zfi${wsz_?o&95r!tUwp{Eg4p6`ftM^|H^yEGV+O{xCfq$F7Ch=qv2H&Mrn(ve7Wh{DFNF zW=q`ci!ih8V4sHBPCpyh*`>_g>}r^us%In7O%u1jT)CZnr7vE-k;882?9Rk2MmSxY0Xt3A@Y@0-+%>I)uS$*3Qm_g>nj^xcf?vXWMMkJETn!<7Cf)iJ zd|UVzxHH!XBSmd+vBU^36f@XdZUhs15*{z91`qD}T}KWmXunx#gda*=;Kn`s=e9uu z`p3^}fpaF~eqS~mpH~g}=rXyq4Jz^YVCfpL;?@ae?ZSO1EXsig+o!>avTCR`86mNp z!M%A#c&&UruX)yt?}pbq>mZA2ooyzIUM1@zi)x(hCyVNv9U+U}6gx>4)irycEUIZ1 zBI_<$7s#SgX4lE0GG^msQ3qY3R3BkwxrSM5h1*X>yCk8~dW^uNFMiMkM%vO&+vq&RV7Ew(zV@32m zD`ECi;LcJr3_X_wZSzy0dD*aVTaBs9i-y1YwcT0@3^2UH3`e(#>J#-jf^bV+(9lG% zuTdfpn%xA_%AEw?t(p=o+=6_|T(x2~o}w(GZ7SjWXV-$IMpQSg$rglru%O{-_0n^T z$RyY0FQ9AbI&vL?1c#^&uEp3B99ryOwqoo^)GCWtfU`~yR;2_7nW&z$4o1U8uLnzW z2Ao@GhPO9}Q0NGO+3mqH&4WGb&5-92;lcV49N1L~-_9?`vh~2BLG8k4SqNUI-5PqKPy(8djz8Mq{jsXqqB1Yr!Cf(G^e9vhl! zQ!pbMLE4`Z%^y${r}pIIuk;JNq3ZRkkCTwJ5B zMWB{NpngT5W<{VzMW8N4pcX}-{zRbWtczwNMh&SiaZ_qaT%?XfM(v1f49bRT3^Z(8 zunEsodtSf~JG%{ghEnmaZw>YGYXrHDU;WgnQ9(9;5+4No8bMYa!4^d@M}p=_Z69RL z2-Xq7+!0KkU^I(^?Bxl{+3pCoH-a6HU?(HkI}vO+g1sBTey6isI{rPK68l30yD-7j zrLR8JvfiTbtRv7DI09uIfwGQ3Sx2BRZ3N0X0%aY6vW`GmN1&`DP}UJB>j;!}1j;%B zWgW8@i1k{Wok{@C9W29n{P18s&f>a5<_yX|x>5cSDE|nQe}pj@KD3-CSmpuCJYJcH zEAwb&9<0n`m3gQ#k5uM?$~;b)hbi+YWgeu=W0ZM_GLKN^WhwJ{A@f-w^N?hAKLKNr zc|G;p{Xe^iVfF2+ktK2n00Sa{@VVO-sMXU;tE0!QbSb{> HcGLd=Pqmd@ delta 3423 zcmZ8k3s6+&74`y3Xb=Sv3l#TOP)NFpf?`wi5Mf!?b$^z7S5~4_E5=0e z(v7a3Ys(})Mv|s8!EtPFnrWk*+Ns@4V<(x!S3qKnX*532$u!e;Y%=LN=gQq~hM9Z5 z@B1J3{Qo&;&*k)~_|vE2PwIKAQoUWiHcw%zE9i4KcLiNuj~+_%Y;ko2{GMQ8hi8*( zv)buz(?iJ~<=J4N8t^F1E}tG6?^D`5TlCOmme;!!cXuI6a5^t%YPz{=SHRopYV#@H zW|{>qIU7durUTgWVCMd;Nx0|Oi`qKeI(%J~GvlE@o`5f?wxLU%em#`L?;u}boh>(Y zvbDVNBkE858zZi|Of9m3z#m=WG z;*%&VZ5CIf?4x4wsl_fRN5n|ns{8bI;$D>fvRZs(vC9c> zh~X$ZcL%P{u9B`pR(`wmA?(htly1P8{2J+FsL#)Z8+nrx9f58=EJl&rGaiP=l;{-u z^x2^j*qfgT2kq07=p>|+qLKr{_6+GNd|@w;KE-D?EGS5kMjoPx5G?3vp%DE{7mMS` z%oa6h>)sKyWTdVjN9kL`E1D9_@d-Fiar^doeVjQSkK;qoIHy3mYiyshT!P;e%5ZP) zPvB0u4c@BFh8G;wuztP`ZaP*&N0|+p3V#e|9X7a7xCU;cUSG5ZE|l6J)BOXuU-UK< z6xm>?xCP#sYlF2V0)BWMDe9?$^!&xud2~oz2ErjSQ#V$gW>EZw(%5rg(5Z#nGPKdHw{DBZn($CzzOk4~o4=Cqyw9xr8Wlg@X`ft*9b2LdZ#ol2trGh!Rz_ z5~3s(Dj`Zxv5gQVr_c~}g%UQY?x0SYfmLrv3(_Sx@q8+@ESh3eRy~slyPhnA`->`I zbnZ0BtZ_pB(>w^fY9erMcNx6fREeSXz+kUz)I63eAxMRWhB?Nu$CsF-$|W1$bz*kx z?^H1profG*PVfa~Xk2zux?;rF+2i1~pQ@M~>2Pv|6HaY2Uq8J*PeSrTV{5}y0%^v; z%5^44Yg}uB9jk*T82`jK3}B(lW>l`hx3w)*;maqR!Ldv>Ha~@qIhL7@U3?lHBSMZX zUyD;;c~-?#oCY)2IU%{*e0$$IT$0?K1}hs1jL(~K2@+$WOO?Rcp{;+aW_rAOdCU6-@hVXx@l^ zdu2GcF@h!VXWx8^%7LH{rdG+ui@~iDf>a~3t51T1dsHln94OiBgu{L2QIBj^BqV9Z zjP5-Wq^o97!)2M^*y@Das%*Tp6))qqYTn;}wk>61G;ZH4!Q2&P@J-JEgjbqp{_Bni z>~1%=c<@{+tn}Zv@WxX!!y- zRFMJS)0}Wf$VRW0At6XLPV{*gfE>Cc4IBRrjY!fktO}$ZTF&ZjiG*rK6sCdy( z;i93cMMEWvhUyg!6>D9b7_pg_>J&GnBE>|_l4Z47(EV)^v?H!Vu+_c84J7&Df>^pzR)CY_^> zhJMh|P}I>-)X`AX(a?`L8j3m^iaHvKIvR>P8j3m^iaHvKIvR>P8j3m^iaJIwln`+F zI`t5oJyec``PHF%?9FwDo!JzBoJR3SL-9vL@kcWZCl4>@0Bh{9#{O#TuEySK?5xJV zYV4}Uo@(r<#(rw-rp8`s?4-s%YV4xM9%`JH8ut&4dxyp@Y2sco`l7K%8amW_q!B+d zhL4osAtoLz#X~GUx=^}mY(M(7gr73oj_t>1%0R7j7gi7CX8x|bS8p_LTg*toq{hEx z7jH@9;FEzVaTg{*@vBpMUe4i3+(^eJt+@OMi`-K!Q4O%j?bQ+=Kgc3?T1(WYvB*u= z62~X9$o0mhKLRXqFsnD8BE%mA xmU=9Mr}DRfC7!n%&%9byIg6YMC7S=&cyvygu22&H`_t_0?$9^s!LC-v{{Ud_toZ-{ diff --git a/docs/build/doctrees/envs/fancy/airhockey.doctree b/docs/build/doctrees/envs/fancy/airhockey.doctree index 5e584e920d8f0efb3193b9381779304aa8043f6c..3e62aada6a45bf8a39da55803a926c5837218181 100644 GIT binary patch delta 831 zcmZXSUq}>D6vn+fJGLu3GrH?+w&U6^qGd^0RBMr`1wn0^AP5zbt4$pzQyZNJp`v}L z6!xJy<3qh<>_gC-jD!zaK~w}0NTB_LSSlzXB7&YfcU)zuw>#(jzVAEt%>C2+_<(p> zoScbIi%%G{aF5W!dQg%zwioZp4Z^;jlQ<`Q_rscQdn1H1P1qzf1?($!+P+8y4YuN_ zRO9I=&;&?hbDr=BSw#x*-8k*7^=G_;sdKu$+{Q_{RZO^6ALJ7(f-Oqqn4N-Za;WJh z$Qzoz=%;eUKU$&T#}#0Z@H;(+>PSpaE5IuSX0`0rzjrwh+H;F4s3mWoCRRb3YaG@}?h!qo*yFUk|5v7U&VYJ+IR zSI|;IqZ}>!FAzVe_4r&>*e+a9o4t)I61u6e;~)16;e&xT0`f!EV{51qm%^I&=!z;x zsw7wW@ delta 685 zcmbV}PiWI{6vy|{B(8B~X*Ef=)fo|obFE+z2ZC%k*rgx?L7Yw`t(mVSW|AcgVTJB6 zoDeAE#T`TtuOf~S|FMfZs3%3mgI+ughD^q;UPSblpfY;&^5gw}-_QHLKff0v--m>T zaC>Y2im(QN^csdq=DYjz`lL~*T2QmC2Lk4 zlo|P>g&fmHU@ryQ5U)a8Ta2-(Y8e_+5AJCBWOft=XfAu2FZ{(a z4C{|DA)bty>0GZbmOaZd-N1)J5G{E5&!(a^Jd8>U4_LIsU_BM=*y3WOK{Nc=Z=~j=rT9skgAP;NgMj8gm_3$C=R5&%$qzJLsGM diff --git a/docs/build/doctrees/envs/fancy/mujoco.doctree b/docs/build/doctrees/envs/fancy/mujoco.doctree index fac5839646a6afb2f58987c42c41550b33299965..12dd8a40556580c359ed011c756672e5a0e7012f 100644 GIT binary patch delta 140 zcmccH%5u4xg{6UYD&s~LeQlP^TSe!jsMyG|T=OH%njLAz( z#3tV^8&H}5!eesRfU$8UC%KYjH9u{S$@)8gbeFqo3T9y=vNtcS(W(7<4F)&Gf; ayQH|b$}uuBvQOQ|$N&V}Wf>U{FaiMY8!)f{ delta 333 zcmccI%yPGtg{6UYD#Jz=eQnl=L`DXN$+9}~{wbAtiMg4{3W<3s3YmE&sYQv&C7ETZ z3aNQznML_|xv6<23Mr|@ndy0{DGF)%MG7SusX&3U)SUbRup~%hNosLPW?s5Ne%j@ zr3*^iZ7%)#hJ)YGd`bp;?34_#9u`AGL-WZ6|0Z%yJ;}rX2AdiGb2DxgW!%RI04SAp A`2YX_ diff --git a/docs/build/doctrees/index.doctree b/docs/build/doctrees/index.doctree index 9832d59fe7a9b9b5b5df8e95fabd40ff1447d7c4..d93b5aad38cdcc11ea58db75a939d4606d897322 100644 GIT binary patch delta 29 lcmZ3#j&c1u#tqGmjPa9O95Yzr(<^f)TT97p=5taM1pu#33P1n= delta 40 wcmZ3#j&c1u#tqGmj0%%m95X}|(kpWlrev_kPRS7K;Y>@+ORiMd`_. The challenge aims to close the gap between simulated learning and real-world application by focusing on various aspects of robotic operation, such as dealing with disturbances, observation noise, safety, and actuator limitations. The environments available through Fancy Gym allow for the development of agents capable of performing tasks with different levels of complexity. These tasks include hitting and defending in air hockey with both three degrees of freedom (3 DoF) and seven degrees of freedom (7 DoF) configurations. The 7 DoF tasks are based on the KUKA iiwa14 robot model, which is used in the simulations to represent a higher level of control complexity akin to real-world settings. diff --git a/docs/build/html/_sources/envs/fancy/mujoco.md.txt b/docs/build/html/_sources/envs/fancy/mujoco.md.txt index c58ded5..018d901 100644 --- a/docs/build/html/_sources/envs/fancy/mujoco.md.txt +++ b/docs/build/html/_sources/envs/fancy/mujoco.md.txt @@ -32,7 +32,7 @@ Variations of this environment are available, differing in reward structures and -The table tennis task offers a dynamic and interactive environment designed for the development and testing of reinforcement learning (RL) systems. Using a robotic arm equipped with seven degrees of freedom (DoFs), the challenge is to respond to incoming balls and return them accurately to a specified goal location on the opponent's side of the table. +The table tennis task offers a robotic arm equipped with seven degrees of freedom (DoFs). The task is to respond to incoming balls and return them accurately to a specified goal location on the opponent's side of the table. The context space for this environment includes the initial ball position, with x-coordinates ranging from -1 to -0.2 meters and y-coordinates from -0.65 to 0.65 meters, and the goal position with x-coordinates between -1.2 to -0.2 meters and y-coordinates from -0.6 to 0.6 meters. The full observation space comprises the sine and cosine values of the joint angles, the joint velocities, and the ball's velocity, providing comprehensive information for the RL system to base its decisions on. @@ -118,4 +118,4 @@ No longer used? ## MP Environments -Many of these envs also exist as MP-variants. Refer to them using `fancy_DMP/` `fancy_ProMP/` or `fancy_ProDMP/`. +Most of these envs also exist as MP-variants. Refer to them using `fancy_DMP/` `fancy_ProMP/` or `fancy_ProDMP/`. diff --git a/docs/build/html/_sources/index.rst.txt b/docs/build/html/_sources/index.rst.txt index 109cc87..7d2f054 100644 --- a/docs/build/html/_sources/index.rst.txt +++ b/docs/build/html/_sources/index.rst.txt @@ -134,7 +134,7 @@ Explore the MP-based variant (`or learn more about Movement Primitives (MPs)

AirHockey

-

Fancy Gym provides access to a range of environments for the Robot Air Hockey Challenge, facilitating research in robot learning. The challenge aims to close the gap between simulated learning and real-world application by focusing on various aspects of robotic operation, such as dealing with disturbances, observation noise, safety, and actuator limitations.

+

Fancy Gym provides access to a range of environments for the Robot Air Hockey Challenge. The challenge aims to close the gap between simulated learning and real-world application by focusing on various aspects of robotic operation, such as dealing with disturbances, observation noise, safety, and actuator limitations.

The environments available through Fancy Gym allow for the development of agents capable of performing tasks with different levels of complexity. These tasks include hitting and defending in air hockey with both three degrees of freedom (3 DoF) and seven degrees of freedom (7 DoF) configurations. The 7 DoF tasks are based on the KUKA iiwa14 robot model, which is used in the simulations to represent a higher level of control complexity akin to real-world settings.

Participants in the challenge are required to develop strategies that enable their robots to react and adapt within these dynamic environments. The final phase of the challenge involves a tournament where the developed agents will be tested in a comprehensive game scenario, both in simulation and, for the top teams, on actual robotic systems.

For detailed information on the challenge, including rules, stages, and submission requirements, please visit the official Robot Air Hockey Challenge website.

diff --git a/docs/build/html/envs/fancy/mujoco.html b/docs/build/html/envs/fancy/mujoco.html index 0d07dfb..2164308 100644 --- a/docs/build/html/envs/fancy/mujoco.html +++ b/docs/build/html/envs/fancy/mujoco.html @@ -172,7 +172,7 @@
-

The table tennis task offers a dynamic and interactive environment designed for the development and testing of reinforcement learning (RL) systems. Using a robotic arm equipped with seven degrees of freedom (DoFs), the challenge is to respond to incoming balls and return them accurately to a specified goal location on the opponent’s side of the table.

+

The table tennis task offers a robotic arm equipped with seven degrees of freedom (DoFs). The task is to respond to incoming balls and return them accurately to a specified goal location on the opponent’s side of the table.

The context space for this environment includes the initial ball position, with x-coordinates ranging from -1 to -0.2 meters and y-coordinates from -0.65 to 0.65 meters, and the goal position with x-coordinates between -1.2 to -0.2 meters and y-coordinates from -0.6 to 0.6 meters. The full observation space comprises the sine and cosine values of the joint angles, the joint velocities, and the ball’s velocity, providing comprehensive information for the RL system to base its decisions on.

A task is considered successfully completed when the returned ball not only lands on the opponent’s side of the table but also within a tight margin of 20 centimeters from the goal location. The reward function is designed to reflect various conditions of play, including whether the ball was hit, if it landed on the table, and the proximity of the ball’s landing position to the goal location.

Variations of the table tennis environment are available to cater to different research needs. These variations maintain the foundational challenge of precise ball return while providing additional complexity for RL algorithms to overcome.

@@ -405,7 +405,7 @@ No longer used?

MP Environments

-

Many of these envs also exist as MP-variants. Refer to them using fancy_DMP/<name> fancy_ProMP/<name> or fancy_ProDMP/<name>.

+

Most of these envs also exist as MP-variants. Refer to them using fancy_DMP/<name> fancy_ProMP/<name> or fancy_ProDMP/<name>.

diff --git a/docs/build/html/index.html b/docs/build/html/index.html index 6251999..2430040 100644 --- a/docs/build/html/index.html +++ b/docs/build/html/index.html @@ -269,7 +269,7 @@ PRs to integrate these environments into

Citing the Project

-

To cite fancy gym in publications:

+

To cite fancy_gym in publications:

@software{fancy_gym,
     title = {Fancy Gym},
     author = {Otto, Fabian and Celik, Onur and Roth, Dominik and Zhou, Hongyi},
diff --git a/docs/build/html/searchindex.js b/docs/build/html/searchindex.js
index 6698ac4..9daa54b 100644
--- a/docs/build/html/searchindex.js
+++ b/docs/build/html/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"docnames": ["api", "envs/dmc", "envs/fancy/airhockey", "envs/fancy/classic_control", "envs/fancy/index", "envs/fancy/mujoco", "envs/meta", "envs/open_ai", "examples/dmc", "examples/general", "examples/metaworld", "examples/movement_primitives", "examples/mp_params_tuning", "examples/open_ai", "examples/pd_control_gain_tuning", "examples/replanning_envs", "generated/fancy_gym.envs", "generated/fancy_gym.register", "generated/fancy_gym.upgrade", "guide/basic_usage", "guide/episodic_rl", "guide/installation", "guide/upgrading_envs", "index"], "filenames": ["api.rst", "envs/dmc.md", "envs/fancy/airhockey.rst", "envs/fancy/classic_control.md", "envs/fancy/index.rst", "envs/fancy/mujoco.md", "envs/meta.md", "envs/open_ai.md", "examples/dmc.rst", "examples/general.rst", "examples/metaworld.rst", "examples/movement_primitives.rst", "examples/mp_params_tuning.rst", "examples/open_ai.rst", "examples/pd_control_gain_tuning.rst", "examples/replanning_envs.rst", "generated/fancy_gym.envs.rst", "generated/fancy_gym.register.rst", "generated/fancy_gym.upgrade.rst", "guide/basic_usage.rst", "guide/episodic_rl.rst", "guide/installation.rst", "guide/upgrading_envs.rst", "index.rst"], "titles": ["API", "DeepMind Control (DMC)", "AirHockey", "Classic Control", "Fancy", "Mujoco", "Metaworld", "Gymnasium", "DeepMind Control Examples", "General Usage Examples", "Metaworld Examples", "Movement Primitives Examples", "MP Params Tuning Example", "OpenAI Envs Examples", "PD Control Gain Tuning Example", "Replanning Example", "fancy_gym.envs", "fancy_gym.register", "fancy_gym.upgrade", "Basic Usage", "What is Episodic RL?", "Installation", "Creating new MP Environments", "Fancy Gym"], "terms": {"These": [1, 2, 3, 5, 7, 20], "ar": [1, 2, 3, 4, 5, 7, 8, 10, 11, 14, 17, 19, 20, 21, 22], "wrapper": [1, 8, 10, 11, 15, 17, 18, 22], "select": [1, 7, 22], "order": 1, "us": [1, 2, 5, 6, 9, 11, 15, 17, 18, 19, 20, 21, 22, 23], "our": [1, 8, 9, 10, 11, 20, 23], "motion": [1, 5, 20], "primit": [1, 8, 10, 13, 17, 18, 20, 22, 23], "gym": [1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 19, 22], "interfac": [1, 6, 10, 11, 22, 23], "them": [1, 5, 6, 7, 8, 10, 11, 19, 23], "when": [1, 5, 8, 9, 10, 17, 22], "instal": [1, 10, 23], "fancy_gym": [1, 6, 8, 9, 10, 11, 12, 13, 14, 15, 19, 21, 22, 23], "option": [1, 5, 17, 18, 19, 21], "extra": 1, "e": [1, 8, 10, 11, 21, 22], "g": [1, 8, 10, 11, 22], "pip": [1, 21, 23], "all": [1, 5, 6, 9, 10, 19, 21, 23], "regular": [1, 19, 23], "task": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 19, 22], "avaibl": [1, 6, 21], "via": [1, 3, 6, 19, 21, 22, 23], "shimmi": 1, "name": [1, 3, 5, 6, 7, 8, 10, 19], "descript": [1, 3, 5, 6, 7, 19], "action": [1, 3, 5, 6, 7, 8, 9, 10, 11, 14, 15, 19, 20, 22, 23], "dim": 1, "observ": [1, 2, 3, 5, 6, 8, 9, 10, 11, 19, 20, 22, 23], "dm_control": [1, 8, 19], "acrobot": 1, "swingup": 1, "v0": [1, 2, 3, 4, 5, 7, 8, 9, 11, 12, 14, 15, 17, 18, 19, 22, 23], "underactu": 1, "doubl": 1, "pendulum": [1, 9], "torqu": [1, 5, 20], "appli": [1, 5], "second": 1, "joint": [1, 5, 22], "swing": 1, "up": [1, 4, 6, 21], "balanc": 1, "1": [1, 5, 7, 8, 9, 10, 11, 13, 14, 15, 19, 22, 23], "6": [1, 5, 6], "swingup_spars": 1, "similar": 1, "spars": [1, 5], "reward": [1, 3, 5, 8, 9, 10, 11, 13, 15, 19, 22, 23], "achiev": [1, 5, 8, 10], "ball_in_cup": [1, 8, 19], "catch": [1, 8, 19], "planar": 1, "ball": [1, 5], "cup": [1, 5], "where": [1, 2, 3, 6], "receptacl": 1, "must": [1, 6], "2": [1, 3, 5, 7, 8, 9, 10, 11, 13, 22], "8": [1, 5, 15], "cartpol": 1, "cart": 1, "pole": 1, "goal": [1, 3, 5, 10], "i": [1, 2, 5, 6, 8, 9, 10, 11, 13, 15, 17, 18, 19, 22, 23], "an": [1, 5, 6, 7, 8, 10, 17, 18, 19, 20, 22, 23], "unactu": 1, "move": 1, "start": [1, 22], "upright": 1, "5": [1, 3, 5, 8, 10, 11, 14, 15, 19, 22], "balance_spars": 1, "downward": 1, "requir": [1, 2, 3, 5, 6, 8, 10, 19, 20, 22], "two_pol": 1, "extens": 1, "domain": 1, "two": [1, 5], "serial": 1, "connect": 1, "increas": [1, 9], "challeng": [1, 2, 5, 23], "three_pol": 1, "three": [1, 2], "further": [1, 19, 20], "11": [1, 8], "cheetah": 1, "run": [1, 8, 9, 10, 11, 13, 15], "biped": 1, "robot": [1, 2, 5, 6, 20, 23], "The": [1, 2, 3, 5, 6, 8, 10, 11, 17, 18, 19, 20, 22, 23], "proport": 1, "forward": 1, "veloc": [1, 5, 11, 14, 15, 19, 20, 22], "maximum": [1, 15], "speed": 1, "17": 1, "dog": 1, "stand": 1, "focus": [1, 2], "postur": 1, "38": 1, "223": 1, "walk": 1, "coordin": [1, 5], "movement": [1, 8, 10, 13, 17, 18, 20, 22, 23], "trot": 1, "perform": [1, 2, 5], "gait": 1, "combin": 1, "stabil": 1, "fetch": 1, "plai": [1, 5, 6], "involv": [1, 2, 6], "locomot": 1, "object": [1, 5, 6, 20], "interact": [1, 5, 19], "232": 1, "finger": 1, "spin": 1, "rotat": 1, "bodi": 1, "hing": 1, "9": [1, 3], "turn_easi": 1, "align": [1, 5, 20], "tip": 1, "free": [1, 19, 22], "target": [1, 14], "easier": 1, "version": [1, 7, 8, 10, 13, 17, 18, 19, 21, 22], "larger": 1, "12": 1, "turn_hard": 1, "smaller": 1, "difficulti": [1, 23], "fish": [1, 8, 10], "right": [1, 20], "itself": [1, 3], "fluid": 1, "21": [1, 5], "swim": [1, 8, 10], "incorpor": 1, "dynam": [1, 2, 5, 20, 23], "24": 1, "hopper": [1, 5], "One": 1, "leg": 1, "minim": 1, "torso": 1, "height": 1, "4": [1, 5, 6, 7, 9, 11, 15, 22], "15": [1, 5, 14], "hop": 1, "humanoid": 1, "simplifi": 1, "maintain": [1, 5, 19, 23], "67": 1, "specifi": [1, 5, 8, 10, 18], "aim": [1, 2], "high": [1, 3, 14], "horizont": 1, "run_pure_st": 1, "focu": [1, 3], "pure": 1, "state": [1, 15, 19], "55": 1, "humanoid_cmu": 1, "advanc": [1, 5, 6], "cmu": 1, "model": [1, 2], "56": 1, "137": 1, "lqr": 1, "lqr_2_1": 1, "linear": [1, 8, 10, 11, 22], "quadrat": 1, "regul": 1, "mass": 1, "actuat": [1, 2], "posit": [1, 5, 14, 19, 20, 22], "optim": [1, 20], "lqr_6_2": 1, "more": [1, 9, 13, 19, 20, 22, 23], "complex": [1, 2, 3, 5], "manipul": [1, 5, 6, 8, 9], "bring_bal": 1, "bring": 1, "locat": [1, 5], "initi": [1, 5], "variat": [1, 4], "44": 1, "bring_peg": 1, "peg": [1, 6], "insert_bal": 1, "insert": [1, 6], "basket": [1, 5], "insert_peg": 1, "slot": 1, "classic": [1, 4, 20, 23], "invert": 1, "limit": [1, 2, 5], "multipl": [1, 5, 8, 10, 11, 13, 18, 19, 22], "3": [1, 2, 5, 22], "point_mass": 1, "easi": [1, 22, 23], "point": [1, 3, 17, 22], "correspond": 1, "global": 1, "x": [1, 5], "y": [1, 5], "ax": [1, 5, 14], "hard": 1, "random": [1, 5], "gain": [1, 23], "per": [1, 5], "episod": [1, 5, 8, 9, 10, 11, 14, 19, 23], "memoryless": 1, "agent": [1, 2, 3], "quadrup": 1, "four": 1, "78": 1, "escap": 1, "environment": 1, "101": 1, "90": 1, "reacher": [1, 5, 7, 11, 13, 19], "link": [1, 3, 5], "sphere": 1, "stacker": 1, "stack_2": 1, "stack": [1, 9], "box": [1, 4, 6, 11, 20, 23], "correct": [1, 14], "placement": 1, "gripper": 1, "49": 1, "stack_4": 1, "63": 1, "swimmer": 1, "swimmer6": 1, "six": 1, "nose": 1, "insid": 1, "25": [1, 3, 5, 15], "swimmer15": 1, "fifteen": 1, "extend": 1, "14": 1, "61": 1, "walker": [1, 5], "trajectori": [1, 3, 7, 8, 10, 11, 13, 14, 19, 20, 22, 23], "horizon": [1, 3, 5, 6, 7], "dimens": [1, 3, 5, 6, 7, 22], "context": [1, 3, 5, 6, 11, 19, 20, 22], "dm_control_prodmp": 1, "A": [1, 3, 5, 6, 7, 10, 22], "promp": [1, 7, 8, 10, 11, 13, 17, 18, 19, 20, 22, 23], "wrap": [1, 7], "1000": [1, 8, 9, 10, 11, 19, 23], "10": [1, 8, 9, 10, 11, 13, 23], "dm_control_dmp": [1, 19], "dmp": [1, 3, 6, 8, 9, 10, 11, 17, 18, 19, 20, 22, 23], "fanci": [2, 3, 5, 9, 11, 19], "provid": [2, 3, 5, 7, 8, 10, 11, 17, 18, 19, 21], "access": [2, 19, 22, 23], "rang": [2, 5, 8, 9, 10, 11, 13, 15, 19, 22, 23], "environ": [2, 4, 8, 9, 10, 11, 13, 14, 15, 17, 18, 20, 21], "air": 2, "hockei": 2, "facilit": 2, "research": [2, 3, 5, 23], "learn": [2, 3, 5, 6, 11, 19, 20, 23], "close": [2, 5, 6, 8, 10, 11, 15], "gap": 2, "between": [2, 5, 14, 19], "simul": [2, 3, 6], "real": [2, 14], "world": [2, 10], "applic": 2, "variou": [2, 5, 23], "aspect": 2, "oper": [2, 20], "deal": 2, "disturb": 2, "nois": 2, "safeti": 2, "avail": [2, 5, 19, 22], "through": [2, 11], "allow": [2, 3, 8, 10, 11, 17, 18, 19, 22], "develop": [2, 5], "capabl": [2, 5], "differ": [2, 5, 8, 10, 14, 18, 20], "level": [2, 19], "includ": [2, 5, 9, 17, 18, 23], "hit": [2, 5], "defend": 2, "both": [2, 22, 23], "degre": [2, 5, 23], "freedom": [2, 5], "dof": [2, 5], "seven": [2, 5], "7": [2, 5], "configur": [2, 5, 17, 18, 22], "base": [2, 4, 8, 9, 10, 11, 13, 15, 17, 18, 20, 22, 23], "kuka": 2, "iiwa14": 2, "which": [2, 3, 5, 8, 10, 11, 13, 17], "repres": [2, 20, 22], "higher": [2, 23], "control": [2, 4, 19, 20, 22, 23], "akin": 2, "set": [2, 8, 9, 10, 17, 19, 20, 23], "particip": 2, "strategi": 2, "enabl": [2, 11, 19], "react": 2, "adapt": [2, 4, 5], "within": [2, 5], "final": [2, 5], "phase": 2, "tournament": 2, "test": [2, 5, 19, 21], "comprehens": [2, 5, 23], "game": [2, 5, 6], "scenario": 2, "top": [2, 5, 6], "team": 2, "actual": 2, "system": [2, 5], "For": [2, 5, 8, 10, 13, 22], "detail": [2, 19, 22], "inform": [2, 5, 13, 14, 19], "rule": 2, "stage": 2, "submiss": [2, 23], "pleas": [2, 14, 18, 22], "visit": 2, "offici": 2, "websit": 2, "follow": [2, 5, 8, 10, 11, 22], "7dof": 2, "3dof": 2, "airhockit2023": 2, "foundat": [3, 5, 21, 23], "platform": 3, "explor": [3, 23], "experi": 3, "rl": [3, 5, 23], "algorithm": [3, 5], "design": [3, 4, 5, 6, 20], "simpl": 3, "practition": 3, "fundament": 3, "principl": 3, "without": [3, 19, 22], "dimension": [3, 22], "physic": [3, 8], "simplereach": 3, "reach": [3, 5, 6, 19], "ani": [3, 9, 17, 18, 19], "until": 3, "150": [3, 6], "time": [3, 5, 8, 10, 11, 19, 23], "thi": [3, 5, 6, 8, 9, 10, 11, 14, 19, 20, 22, 23], "space": [3, 5, 11, 20, 22], "precis": [3, 5], "toward": 3, "end": [3, 5], "200": [3, 5, 9], "longsimplereach": 3, "18": [3, 5], "viapointreach": 3, "leverag": [3, 9], "support": [3, 6, 10, 19, 20, 22, 23], "self": [3, 22], "collis": 3, "detect": 3, "onli": [3, 5, 8, 10, 17, 19, 21, 22], "100": [3, 5, 7, 15], "199": 3, "viapoint": 3, "respect": 3, "holereach": [3, 9, 11], "effector": [3, 5], "need": [3, 5, 8, 10, 18, 22], "narrow": 3, "hole": [3, 6], "colld": 3, "wall": [3, 6], "fancy_dmp": [3, 5, 11], "holereacherfixedgo": 3, "fix": [3, 5, 10], "attractor": 3, "30": 3, "add": [4, 8, 10, 19, 22], "coupl": 4, "new": [4, 11, 18, 19, 20, 23], "some": [4, 11, 14, 19], "exist": [4, 6, 8, 10, 11, 17, 18, 19, 22], "while": [4, 5, 15, 19, 20], "other": [4, 8, 10, 19, 22, 23], "were": 4, "build": [4, 22], "u": 4, "from": [4, 5, 6, 8, 9, 10, 14, 19, 20, 22, 23], "ground": [4, 5], "push": [4, 6, 23], "boxpushingdens": [4, 5, 15, 23], "mujoco": [4, 9, 11, 15, 21, 23], "step": [4, 8, 9, 10, 11, 13, 14, 15, 17, 18, 20, 22, 23], "tabl": [4, 23], "tenni": [4, 23], "beer": 4, "pong": 4, "mp": [4, 8, 10, 11, 14, 17, 18, 19, 20, 23], "airhockei": [4, 23], "present": [5, 20, 23], "reinforc": [5, 6, 23], "util": 5, "versatil": 5, "franka": 5, "emika": 5, "panda": [5, 23], "arm": [5, 6], "boast": 5, "orient": 5, "defin": [5, 11, 18, 22], "its": [5, 10], "constrain": 5, "certain": 5, "along": 5, "encompass": 5, "full": [5, 8, 10, 11, 13, 19, 22, 23], "360": 5, "z": 5, "axi": [5, 14], "": [5, 20, 23], "mission": 5, "accuraci": 5, "centimet": 5, "0": [5, 8, 9, 10, 11, 13, 14, 15, 19, 22], "radian": 5, "sine": 5, "cosin": 5, "valu": [5, 9, 14, 19], "angl": 5, "quaternion": 5, "describ": 5, "each": [5, 19], "composit": 5, "function": [5, 9, 11], "serv": 5, "metric": 5, "It": [5, 8, 10, 11, 22], "account": 5, "distanc": 5, "rod": 5, "desir": [5, 15], "penalti": 5, "violat": 5, "well": [5, 19, 22], "cost": 5, "energi": 5, "expenditur": 5, "structur": [5, 6, 8, 10, 11], "purposefulli": 5, "enhanc": [5, 20], "gener": [5, 11, 15, 19, 20, 22, 23], "tempor": 5, "last": [5, 11], "timestep": 5, "spatial": 5, "almost": 5, "enought": 5, "somewhat": 5, "correctli": 5, "custom": [5, 8, 9, 10, 11, 15, 18, 19, 22, 23], "dens": 5, "13": 5, "boxpushingtemporalspars": [5, 11], "boxpushingtemporalspatialspars": 5, "offer": [5, 23], "equip": [5, 6], "respond": 5, "incom": 5, "return": [5, 8, 9, 10, 11, 12, 13, 19, 22], "accur": 5, "oppon": 5, "side": [5, 6], "meter": 5, "65": 5, "compris": [5, 6], "decis": 5, "consid": 5, "successfulli": 5, "complet": [5, 20], "land": 5, "also": [5, 6, 8, 9, 10, 11, 17, 18, 19, 21], "tight": 5, "margin": 5, "20": [5, 11], "reflect": 5, "condit": [5, 15], "whether": [5, 17, 22, 23], "wa": 5, "proxim": 5, "cater": 5, "addit": [5, 17, 18, 19], "overcom": 5, "tabletennis2d": 5, "2d": 5, "350": 5, "19": 5, "tabletennis2dreplan": 5, "replan": [5, 11, 19, 23], "tabletennis4d": [5, 11, 12], "4d": 5, "22": 5, "tabletennis4dreplan": [5, 11], "tabletenniswind": 5, "wind": 5, "effect": [5, 22], "tabletennisgoalswitch": 5, "switch": 5, "tabletenniswindreplan": [5, 11], "upon": [5, 23], "throw": 5, "place": [5, 6], "larg": 5, "establish": 5, "42": [5, 18], "05": [5, 14], "angular": 5, "rel": [5, 22], "bottom": 5, "current": [5, 6, 8, 10, 19, 20, 22], "method": [5, 8, 10, 11, 20, 23], "paramet": [5, 8, 10, 11, 18, 22, 23], "expand": 5, "weight": 5, "basi": [5, 11, 20], "durat": 5, "releas": 5, "implement": [5, 11, 19, 22], "form": 5, "squar": 5, "sum": [5, 11], "across": 5, "penal": 5, "excess": 5, "forc": 5, "encourag": [5, 23], "effici": [5, 6], "t": [5, 11, 14, 15], "befor": 5, "non": [5, 18], "markovian": 5, "contact": 5, "touch": 5, "ha": [5, 8, 10, 21, 22], "made": 5, "compon": [5, 6], "assess": 5, "chosen": [5, 20], "ensur": 5, "fall": 5, "reason": 5, "overal": 5, "specif": [5, 13, 20], "success": 5, "determin": [5, 22], "conclus": 5, "showcas": 5, "abil": 5, "predict": [5, 20], "execut": [5, 11, 19, 20, 23], "popular": 5, "parti": [5, 21], "beerpong": 5, "300": 5, "29": 5, "beerpongstepbas": 5, "beerpongfixedreleas": 5, "modifi": 5, "gymnasium": [5, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 22, 23], "v2": [5, 6, 7, 9, 10, 13, 19], "reacherspars": 5, "same": [5, 8, 10, 11, 17, 18, 19, 22], "longreach": 5, "27": 5, "longreacherspars": 5, "reacher5d": [5, 9, 11, 14, 19], "env": [5, 6, 8, 9, 10, 11, 14, 15, 17, 18, 19, 22, 23], "reacherenv": 5, "reacher5dspars": 5, "reacher7d": 5, "reacher7dspars": 5, "hopperjumpspars": 5, "jump": 5, "250": [5, 8], "16": [5, 9], "hopperjump": 5, "continu": 5, "antjump": 5, "ant": 5, "119": 5, "halfcheetahjump": 5, "halfcheetah": [5, 9], "112": 5, "hopperjumponbox": 5, "hopperthrow": 5, "hopperthrowinbasket": 5, "walker2djump": 5, "walker2d": 5, "depend": [5, 20, 21], "mani": [5, 11], "variant": [5, 6, 19, 23], "refer": [5, 6, 7], "fancy_promp": [5, 11, 12, 14, 19, 23], "fancy_prodmp": [5, 11, 12, 15], "dial": 6, "turn": [6, 19], "open": [6, 19, 22], "sourc": [6, 17, 18], "benchmark": [6, 23], "meta": [6, 10], "multi": 6, "50": [6, 7], "divers": 6, "featur": 6, "univers": 6, "tabletop": 6, "sawyer": 6, "varieti": [6, 11], "everydai": 6, "share": 6, "pivot": 6, "reus": 6, "acquir": 6, "relat": 6, "make": [6, 8, 9, 10, 11, 12, 13, 14, 15, 19, 22, 23], "ml1": [6, 19], "standard": [6, 8, 10, 23], "assembli": 6, "assembl": 6, "39": 6, "basketbal": 6, "bin": 6, "pick": [6, 18], "button": [6, 10], "press": [6, 10], "topdown": 6, "down": 6, "perspect": 6, "coffe": 6, "machin": 6, "pull": 6, "lever": 6, "disassembl": 6, "door": 6, "lock": 6, "unlock": 6, "hand": [6, 22], "drawer": 6, "faucet": 6, "hammer": 6, "handl": [6, 14], "out": [6, 23], "back": [6, 11], "backward": 6, "plate": 6, "slide": 6, "unplug": 6, "soccer": 6, "stick": 6, "against": 6, "shelf": 6, "sweep": 6, "contain": 6, "window": 6, "metaworld_promp": [6, 10], "metaworld_prodmp": [6, 19], "now": [6, 10, 11], "lunar": 7, "lander": 7, "lunarland": 7, "we": [7, 8, 10, 11, 18, 19, 20, 21, 22, 23], "farama": [7, 21], "previous": 7, "openai": [7, 9, 19, 23], "doc": 7, "overview": 7, "counterpart": 7, "gym_promp": [7, 13, 19], "continuousmountaincar": 7, "fetchslidedens": 7, "v1": [7, 9, 10], "fetchreachdens": 7, "import": [8, 9, 10, 11, 12, 13, 14, 15, 19, 22, 23], "def": [8, 9, 10, 11, 12, 13, 15, 22], "example_dmc": 8, "env_id": [8, 9, 10, 11, 13, 14, 15], "seed": [8, 9, 10, 11, 13, 14, 15, 19], "iter": [8, 9, 10, 11, 15], "render": [8, 9, 10, 11, 13, 14, 15, 19, 23], "true": [8, 9, 10, 11, 12, 13, 14, 15, 17, 19], "dmc": [8, 9, 21, 23], "domain_nam": [8, 9], "task_nam": [8, 9, 10], "environment_nam": [8, 9], "arg": [8, 9, 10, 11, 13, 17, 18], "either": [8, 9, 14], "determinist": [8, 9, 10, 11], "behaviour": [8, 9, 10, 11], "number": [8, 9, 10, 11, 13, 15, 19, 22], "rollout": [8, 9, 10, 11], "ob": [8, 9, 10, 11, 13, 15], "reset": [8, 9, 10, 11, 13, 14, 15, 19, 22, 23], "print": [8, 9, 10, 11, 13, 17, 19, 22], "shape": [8, 9, 10, 14, 22], "observation_spac": [8, 9, 10, 22], "action_spac": [8, 9, 10, 11, 13, 14, 15, 19, 22, 23], "ac": [8, 10, 11, 13, 15, 22], "sampl": [8, 9, 10, 11, 13, 14, 15, 19, 22, 23], "mode": [8, 10, 11, 13, 14, 15, 19], "human": [8, 10, 11, 13, 15, 19, 23], "termin": [8, 9, 10, 11, 13, 15, 19, 22, 23], "truncat": [8, 9, 10, 11, 13, 15, 19, 22, 23], "info": [8, 9, 10, 11, 13, 15, 19, 22, 23], "del": [8, 10, 15], "example_custom_dmc_and_mp": 8, "alreadi": [8, 10, 11, 13, 17, 18, 19, 22], "regist": [8, 10, 11, 13, 15, 18, 22, 23], "henc": [8, 10, 11, 19], "adjust": [8, 10, 11], "hyperparamet": [8, 10, 11], "yet": [8, 10, 11, 21, 22], "recommend": [8, 10, 11, 22, 23], "abov": [8, 9, 10, 11, 19], "you": [8, 10, 11, 17, 18, 19, 21, 22, 23], "just": [8, 10, 11, 19], "interest": [8, 10, 11], "chain": [8, 10], "those": [8, 10, 11, 21], "appreci": [8, 10, 11, 23], "pr": [8, 10, 11, 22, 23], "especi": [8, 10, 11], "repo": [8, 10, 11], "http": [8, 10, 11, 21, 23], "github": [8, 10, 11, 21, 23], "com": [8, 10, 11, 21, 23], "alrhub": [8, 10, 11, 21, 23], "accord": [8, 10], "base_env_id": [8, 10, 11, 15], "replac": [8, 10], "your": [8, 10, 14, 22, 23], "inherit": [8, 10], "rawinterfacewrapp": [8, 10, 17, 18, 22], "can": [8, 10, 11, 15, 17, 18, 19, 21, 22, 23], "case": [8, 10, 19, 22], "thei": [8, 10, 11, 20, 21], "suit": [8, 20, 23], "mpwrapper": [8, 10, 11, 15], "trajectory_generator_kwarg": [8, 10, 11, 15], "trajectory_generator_typ": [8, 10, 11, 15], "phase_generator_kwarg": [8, 10, 11, 15, 22], "phase_generator_typ": [8, 10, 11, 15, 22], "controller_kwarg": [8, 10, 11, 14, 15, 22], "controller_typ": [8, 10, 11, 15], "motor": 8, "p_gain": [8, 14, 22], "d_gain": [8, 14, 22], "basis_generator_kwarg": [8, 10, 11, 15, 22], "basis_generator_typ": [8, 10, 11, 15], "zero_rbf": [8, 10, 11], "num_basi": [8, 10, 11, 15, 22], "num_basis_zero_start": [8, 10, 11, 22], "exp": [8, 10, 11, 15], "alpha_phas": [8, 10, 11], "rbf": [8, 10, 11], "make_bb": [8, 10, 15], "black_box_kwarg": [8, 10, 15], "traj_gen_kwarg": [8, 10, 15], "phase_kwarg": [8, 10, 15], "basis_kwarg": [8, 10, 15], "call": [8, 10, 19], "onc": [8, 10, 19, 20], "begin": [8, 10, 19], "everi": [8, 10, 11, 19, 20], "consecut": [8, 10], "none": [8, 10, 11, 17, 18, 19], "possibl": [8, 10, 11], "chang": [8, 10, 11, 19, 22], "nth": [8, 10], "should": [8, 10, 18, 22], "displai": [8, 10], "__name__": [8, 9, 10, 11, 12, 13, 15], "__main__": [8, 9, 10, 11, 12, 13, 15], "disclaim": [8, 10], "afterward": [8, 10], "doe": [8, 10], "affect": [8, 10], "underli": [8, 10, 19], "export": [8, 10], "mujoco_gl": 8, "osmesa": 8, "vision": 8, "integr": [8, 22, 23], "yield": 8, "error": 8, "reach_site_featur": 8, "hybrid": [8, 10, 19], "framework": [8, 9, 10, 20, 22, 23], "dm_control_promp": 8, "becaus": [8, 10], "longer": [8, 19], "combo": 8, "collect": [9, 14, 19, 23], "defaultdict": 9, "numpi": [9, 14, 22], "np": [9, 14, 22], "example_gener": 9, "make_env": 9, "id": [9, 15, 17, 18, 19, 22], "example_async": 9, "n_cpu": 9, "int": [9, 22], "533d": 9, "n_sampl": 9, "800": 9, "vector": 9, "multiprocess": 9, "faster": 9, "Be": 9, "awar": 9, "reduc": 9, "total": [9, 19], "length": [9, 19], "individu": [9, 20], "cpu": 9, "core": 9, "parallel": 9, "tupl": [9, 22], "done": [9, 15], "type": [9, 17, 18, 19, 22], "ndarrai": [9, 22], "asyncvectorenv": 9, "make_rank": 9, "OR": 9, "plot": [9, 12, 14], "zero": [9, 14], "buffer": 9, "list": [9, 17, 18, 19], "would": 9, "than": 9, "request": 9, "num_env": 9, "repeat": 9, "ceil": 9, "append": 9, "f": [9, 14], "do": [9, 22], "threshold": 9, "map": 9, "lambda": [9, 15], "v": 9, "basic": [9, 10, 23], "example_meta": 10, "alwai": [10, 19], "found": [10, 19, 20, 23], "here": [10, 11, 19, 20, 22, 23], "arxiv": 10, "org": 10, "pdf": 10, "1910": 10, "10897": 10, "io": 10, "todo": [10, 14], "work": [10, 14, 19], "due": 10, "issu": [10, 19], "code": 10, "TO": 10, "BE": 10, "fals": [10, 11, 15, 17], "FOR": 10, "THE": 10, "remov": 10, "example_custom_meta_and_mp": 10, "goal_object_change_mp_wrapp": 10, "rais": [10, 19, 22], "valueerror": 10, "bug": 10, "temporari": 10, "workaround": 10, "alter": [10, 11], "mujocoenv": 10, "offscreen": 10, "mai": 10, "behavior": 10, "might": [10, 14], "necessari": [10, 19, 22], "opengl": 10, "ld_preload": 10, "usr": 10, "lib": 10, "x86_64": 10, "linux": 10, "gnu": 10, "libglew": 10, "so": [10, 22], "500": [10, 11], "buttonpress": 10, "example_mp": [11, 13], "env_nam": [11, 13, 15], "black": [11, 20, 23], "equival": 11, "have": [11, 20, 21, 22], "creat": [11, 17, 19, 23], "take": 11, "care": 11, "extern": 11, "render_mod": [11, 23], "els": [11, 13], "raw": [11, 17, 18], "parametr": [11, 20], "give": 11, "sub": [11, 19], "equal": 11, "default": [11, 17, 18, 19, 22], "over": 11, "wise": [11, 19], "aggreg": 11, "example_custom_mp": 11, "argument": [11, 17, 19], "mp_config_overrid": [11, 14, 17, 18], "wai": [11, 14, 19], "class": [11, 17, 18, 22], "custom_mpwrapp": 11, "mp_config": [11, 22], "weights_scal": [11, 15], "example_fully_custom_mp": 11, "custom_env_id": 11, "custom_env_id_dmp": 11, "custom_env_id_promp": 11, "upgrad": [11, 17, 22, 23], "mp_wrapper": [11, 15, 17, 18, 22], "add_mp_typ": [11, 17, 18], "base_id": [11, 18], "try": [11, 19, 23], "don": 11, "correlcti": 11, "except": [11, 19], "pass": [11, 17], "example_fully_custom_mp_altern": 11, "instead": [11, 17, 18, 20, 22], "mp_arg": 11, "dure": 11, "registr": [11, 18], "main": 11, "prodmp": [11, 15, 17, 18, 19, 20, 22, 23], "boxpushingdensereplan": [11, 15], "obs1": 11, "compare_bases_shap": 12, "env1_id": 12, "env2_id": 12, "env1": 12, "traj_gen": [12, 13], "show_scaled_basi": 12, "env2": 12, "stuff": 13, "look": [13, 19, 22], "boolean": [13, 22], "ordereddict": 14, "matplotlib": 14, "pyplot": 14, "plt": 14, "howev": [14, 19, 22], "verifi": 14, "extract": 14, "below": 14, "w": 14, "po": [14, 15], "vel": [14, 15], "get_trajectori": 14, "base_shap": 14, "actual_po": 14, "len": 14, "actual_vel": 14, "act": 14, "ion": 14, "fig": 14, "figur": 14, "add_subplot": 14, "img": 14, "imshow": 14, "rgb_arrai": 14, "show": [14, 19], "des_po": 14, "des_vel": 14, "enumer": 14, "zip": 14, "tracking_control": 14, "get_act": 14, "current_po": [14, 22], "current_vel": [14, 22], "clip": 14, "low": 14, "set_data": 14, "canva": 14, "draw": 14, "flush_ev": 14, "figsiz": 14, "subplot": 14, "131": 14, "titl": [14, 23], "p1": 14, "c": 14, "c0": 14, "label": 14, "p2": 14, "c1": 14, "xlabel": 14, "gca": 14, "get_legend_handles_label": 14, "by_label": 14, "legend": 14, "kei": [14, 19], "132": 14, "133": 14, "std": 14, "example_run_replanning_env": 15, "example_custom_replanning_env": 15, "box_push": 15, "max_planning_tim": 15, "plan": 15, "replanning_schedul": 15, "trigger": 15, "condition_on_desir": 15, "boundari": [15, 23], "next": 15, "str": [17, 18], "entry_point": [17, 22], "union": [17, 22], "callabl": 17, "black_box": [17, 18], "raw_interface_wrapp": [17, 18], "registri": [17, 18], "defaultmpwrapp": [17, 18], "register_step_bas": 17, "bool": [17, 22], "dict": [17, 18], "kwarg": 17, "If": [17, 19, 21, 22, 23], "want": [17, 21, 23], "uniqu": [17, 18, 20], "identifi": [17, 18], "entri": 17, "srtep": 17, "dictionari": [17, 18, 19], "overrid": [17, 18], "keyword": 17, "constructor": 17, "note": [17, 18], "otherwis": [17, 18], "given": [17, 19, 22], "string": 17, "notat": 17, "warn": 17, "messag": 17, "suggest": 17, "exampl": [17, 18, 19, 22], "To": [17, 18, 19, 23], "myenv": [17, 18], "myenvclass": 17, "my_modul": 17, "expect": 18, "known_mp": 18, "Will": [18, 23], "match": [18, 22], "wish": 18, "one": [18, 22, 23], "alongsid": 18, "custommpwrapp": 18, "param": [18, 23], "prepar": 19, "ad": 19, "namespac": 19, "legaci": [19, 21], "metaworld": [19, 20, 21, 23], "n": 19, "cumul": 19, "part": [19, 22], "mainli": 19, "meant": 19, "debug": 19, "log": 19, "train": 19, "step_act": 19, "output": 19, "step_observ": 19, "intermedi": 19, "step_reward": 19, "trajectory_length": 19, "origin": 19, "In": [19, 22], "miss": 19, "fill": 19, "_": 19, "keep": 19, "mind": 19, "process": 19, "split": 19, "lean": 19, "still": [19, 22], "beta": 19, "feel": [19, 22], "problem": 19, "occur": 19, "directli": [19, 22], "gym_": 19, "again": 19, "conveni": 19, "variabl": 19, "store": 19, "all_movement_primitive_environ": 19, "all_fancy_movement_primitive_environ": 19, "all_gym_movement_primitive_environ": 19, "deepmind": [19, 23], "all_dmc_movement_primitive_environ": 19, "all_metaworld_movement_primitive_environ": 19, "movement_primitive_environments_for_n": 19, "my_custom_namespac": 19, "tradit": 20, "concept": 20, "stochast": 20, "search": 20, "commonli": 20, "produc": 20, "like": [20, 21], "probabilist": [20, 23], "convert": 20, "track": 20, "pd": [20, 23], "tailor": 20, "addition": 20, "special": 20, "overarch": 20, "remain": 20, "polici": 20, "craft": 20, "accommod": 20, "contextu": [20, 22], "At": 20, "onset": 20, "subset": 20, "demand": 20, "virtual": 21, "venv": 21, "3rd": 21, "altern": [21, 23], "poetri": 21, "conda": 21, "few": 21, "choos": 21, "box2d": 21, "jax": 21, "automat": 21, "date": 21, "sinc": 21, "git": 21, "d155d0051630bb365ea6a824e02c66c068947439": 21, "egg": 21, "clone": 21, "repositori": 21, "go": 21, "folder": 21, "cd": 21, "manual": 21, "guid": 22, "explain": 22, "how": 22, "abc": 22, "abstractmethod": 22, "properti": 22, "context_mask": 22, "mask": 22, "filter": 22, "unwant": 22, "unnecessari": 22, "after": 22, "first": 22, "receiv": 22, "arrai": 22, "indic": 22, "ones": 22, "dtype": 22, "float": 22, "exclus": 22, "regardless": 22, "indirectli": 22, "notimplementederror": 22, "overitten": 22, "attribut": 22, "document": 22, "mp_pytorch": 22, "userguid": 22, "anoth": 22, "merg": 22, "num_basis_zero_go": 22, "rough": 22, "outlin": 22, "shown": 22, "simpli": 22, "cool_new_env": 22, "my_custom_mpwrapp": 22, "my_custom_env": 22, "custom_prodmp": 22, "built": 23, "fork": 23, "renown": 23, "librari": 23, "sever": 23, "etc": 23, "With": 23, "straightforward": 23, "transform": 23, "compat": 23, "contribut": 23, "own": 23, "re": 23, "inspir": 23, "assist": 23, "highli": 23, "randomli": 23, "sleep": 23, "metadata": 23, "render_fp": 23, "about": 23, "pypi": 23, "master": 23, "what": 23, "usag": 23, "tune": 23, "public": 23, "softwar": 23, "author": 23, "otto": 23, "fabian": 23, "celik": 23, "onur": 23, "roth": 23, "dominik": 23, "zhou": 23, "hongyi": 23, "abstract": 23, "unifi": 23, "approach": 23, "url": 23, "organ": 23, "autonom": 23, "lab": 23, "alr": 23, "kit": 23}, "objects": {"fancy_gym": [[16, 0, 0, "-", "envs"], [17, 1, 1, "", "register"], [18, 1, 1, "", "upgrade"]]}, "objtypes": {"0": "py:module", "1": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "function", "Python function"]}, "titleterms": {"api": [0, 23], "deepmind": [1, 8], "control": [1, 3, 8, 14], "dmc": 1, "step": [1, 3, 5, 6, 7, 19], "base": [1, 3, 5, 6, 7, 19], "environ": [1, 3, 5, 6, 7, 19, 22, 23], "mp": [1, 3, 5, 6, 7, 12, 22], "airhockei": 2, "classic": 3, "fanci": [4, 23], "mujoco": 5, "box": [5, 19], "push": 5, "tabl": 5, "tenni": 5, "beer": 5, "pong": 5, "variat": 5, "exist": 5, "metaworld": [6, 10], "gymnasium": 7, "exampl": [8, 9, 10, 11, 12, 13, 14, 15, 23], "gener": 9, "usag": [9, 19], "movement": 11, "primit": 11, "param": 12, "tune": [12, 14], "openai": 13, "env": [13, 16], "pd": 14, "gain": 14, "replan": 15, "fancy_gym": [16, 17, 18], "regist": 17, "upgrad": 18, "basic": 19, "black": 19, "what": 20, "i": 20, "episod": 20, "rl": 20, "instal": 21, "from": 21, "pypi": 21, "recommend": 21, "master": 21, "creat": 22, "new": 22, "gym": 23, "kei": 23, "featur": 23, "quickstart": 23, "guid": 23, "user": 23, "cite": 23, "project": 23, "icon": 23, "attribut": 23}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.viewcode": 1, "sphinx": 57}, "alltitles": {"API": [[0, "api"], [23, null]], "DeepMind Control (DMC)": [[1, "deepmind-control-dmc"]], "Step-Based Environments": [[1, "step-based-environments"], [3, "step-based-environments"], [5, "step-based-environments"], [6, "step-based-environments"], [7, "step-based-environments"], [19, "step-based-environments"]], "MP Environments": [[1, "mp-environments"], [3, "mp-environments"], [5, "mp-environments"], [6, "mp-environments"], [7, "mp-environments"]], "AirHockey": [[2, "airhockey"]], "Classic Control": [[3, "classic-control"]], "Fancy": [[4, "fancy"]], "Mujoco": [[5, "mujoco"]], "Box Pushing": [[5, "box-pushing"]], "Table Tennis": [[5, "table-tennis"]], "Beer Pong": [[5, "beer-pong"]], "Variations of existing environments": [[5, "variations-of-existing-environments"]], "Metaworld": [[6, "metaworld"]], "Gymnasium": [[7, "gymnasium"]], "DeepMind Control Examples": [[8, "deepmind-control-examples"]], "General Usage Examples": [[9, "general-usage-examples"]], "Metaworld Examples": [[10, "metaworld-examples"]], "Movement Primitives Examples": [[11, "movement-primitives-examples"]], "MP Params Tuning Example": [[12, "mp-params-tuning-example"]], "OpenAI Envs Examples": [[13, "openai-envs-examples"]], "PD Control Gain Tuning Example": [[14, "pd-control-gain-tuning-example"]], "Replanning Example": [[15, "replanning-example"]], "fancy_gym.envs": [[16, "module-fancy_gym.envs"]], "fancy_gym.register": [[17, "fancy-gym-register"]], "fancy_gym.upgrade": [[18, "fancy-gym-upgrade"]], "Basic Usage": [[19, "basic-usage"]], "Black-Box Environments": [[19, "black-box-environments"]], "What is Episodic RL?": [[20, "what-is-episodic-rl"]], "Installation": [[21, "installation"]], "Installation from PyPI (recommended)": [[21, "installation-from-pypi-recommended"]], "Installation from master": [[21, "installation-from-master"]], "Creating new MP Environments": [[22, "creating-new-mp-environments"]], "Fancy Gym": [[23, "fancy-gym"]], "Key Features": [[23, "key-features"]], "Quickstart Guide": [[23, "quickstart-guide"]], "User Guide": [[23, null]], "Environments": [[23, null]], "Examples": [[23, null]], "Citing the Project": [[23, "citing-the-project"]], "Icon Attribution": [[23, "icon-attribution"]]}, "indexentries": {"fancy_gym.envs": [[16, "module-fancy_gym.envs"]], "module": [[16, "module-fancy_gym.envs"]], "register() (in module fancy_gym)": [[17, "fancy_gym.register"]], "upgrade() (in module fancy_gym)": [[18, "fancy_gym.upgrade"]]}})
\ No newline at end of file
+Search.setIndex({"docnames": ["api", "envs/dmc", "envs/fancy/airhockey", "envs/fancy/classic_control", "envs/fancy/index", "envs/fancy/mujoco", "envs/meta", "envs/open_ai", "examples/dmc", "examples/general", "examples/metaworld", "examples/movement_primitives", "examples/mp_params_tuning", "examples/open_ai", "examples/pd_control_gain_tuning", "examples/replanning_envs", "generated/fancy_gym.envs", "generated/fancy_gym.register", "generated/fancy_gym.upgrade", "guide/basic_usage", "guide/episodic_rl", "guide/installation", "guide/upgrading_envs", "index"], "filenames": ["api.rst", "envs/dmc.md", "envs/fancy/airhockey.rst", "envs/fancy/classic_control.md", "envs/fancy/index.rst", "envs/fancy/mujoco.md", "envs/meta.md", "envs/open_ai.md", "examples/dmc.rst", "examples/general.rst", "examples/metaworld.rst", "examples/movement_primitives.rst", "examples/mp_params_tuning.rst", "examples/open_ai.rst", "examples/pd_control_gain_tuning.rst", "examples/replanning_envs.rst", "generated/fancy_gym.envs.rst", "generated/fancy_gym.register.rst", "generated/fancy_gym.upgrade.rst", "guide/basic_usage.rst", "guide/episodic_rl.rst", "guide/installation.rst", "guide/upgrading_envs.rst", "index.rst"], "titles": ["API", "DeepMind Control (DMC)", "AirHockey", "Classic Control", "Fancy", "Mujoco", "Metaworld", "Gymnasium", "DeepMind Control Examples", "General Usage Examples", "Metaworld Examples", "Movement Primitives Examples", "MP Params Tuning Example", "OpenAI Envs Examples", "PD Control Gain Tuning Example", "Replanning Example", "fancy_gym.envs", "fancy_gym.register", "fancy_gym.upgrade", "Basic Usage", "What is Episodic RL?", "Installation", "Creating new MP Environments", "Fancy Gym"], "terms": {"These": [1, 2, 3, 5, 7, 20], "ar": [1, 2, 3, 4, 5, 7, 8, 10, 11, 14, 17, 19, 20, 21, 22], "wrapper": [1, 8, 10, 11, 15, 17, 18, 22], "select": [1, 7, 22], "order": 1, "us": [1, 2, 5, 6, 9, 11, 15, 17, 18, 19, 20, 21, 22, 23], "our": [1, 8, 9, 10, 11, 20, 23], "motion": [1, 5, 20], "primit": [1, 8, 10, 13, 17, 18, 20, 22, 23], "gym": [1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 19, 22], "interfac": [1, 6, 10, 11, 22, 23], "them": [1, 5, 6, 7, 8, 10, 11, 19, 23], "when": [1, 5, 8, 9, 10, 17, 22], "instal": [1, 10, 23], "fancy_gym": [1, 6, 8, 9, 10, 11, 12, 13, 14, 15, 19, 21, 22, 23], "option": [1, 5, 17, 18, 19, 21], "extra": 1, "e": [1, 8, 10, 11, 21, 22], "g": [1, 8, 10, 11, 22], "pip": [1, 21, 23], "all": [1, 5, 6, 9, 10, 19, 21, 23], "regular": [1, 19, 23], "task": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 19, 22], "avaibl": [1, 6, 21], "via": [1, 3, 6, 19, 21, 22, 23], "shimmi": 1, "name": [1, 3, 5, 6, 7, 8, 10, 19], "descript": [1, 3, 5, 6, 7, 19], "action": [1, 3, 5, 6, 7, 8, 9, 10, 11, 14, 15, 19, 20, 22, 23], "dim": 1, "observ": [1, 2, 3, 5, 6, 8, 9, 10, 11, 19, 20, 22, 23], "dm_control": [1, 8, 19], "acrobot": 1, "swingup": 1, "v0": [1, 2, 3, 4, 5, 7, 8, 9, 11, 12, 14, 15, 17, 18, 19, 22, 23], "underactu": 1, "doubl": 1, "pendulum": [1, 9], "torqu": [1, 5, 20], "appli": [1, 5], "second": 1, "joint": [1, 5, 22], "swing": 1, "up": [1, 4, 6, 21], "balanc": 1, "1": [1, 5, 7, 8, 9, 10, 11, 13, 14, 15, 19, 22, 23], "6": [1, 5, 6], "swingup_spars": 1, "similar": 1, "spars": [1, 5], "reward": [1, 3, 5, 8, 9, 10, 11, 13, 15, 19, 22, 23], "achiev": [1, 5, 8, 10], "ball_in_cup": [1, 8, 19], "catch": [1, 8, 19], "planar": 1, "ball": [1, 5], "cup": [1, 5], "where": [1, 2, 3, 6], "receptacl": 1, "must": [1, 6], "2": [1, 3, 5, 7, 8, 9, 10, 11, 13, 22], "8": [1, 5, 15], "cartpol": 1, "cart": 1, "pole": 1, "goal": [1, 3, 5, 10], "i": [1, 2, 5, 6, 8, 9, 10, 11, 13, 15, 17, 18, 19, 22, 23], "an": [1, 5, 6, 7, 8, 10, 17, 18, 19, 20, 22, 23], "unactu": 1, "move": 1, "start": [1, 22], "upright": 1, "5": [1, 3, 5, 8, 10, 11, 14, 15, 19, 22], "balance_spars": 1, "downward": 1, "requir": [1, 2, 3, 5, 6, 8, 10, 19, 20, 22], "two_pol": 1, "extens": 1, "domain": 1, "two": [1, 5], "serial": 1, "connect": 1, "increas": [1, 9], "challeng": [1, 2, 5, 23], "three_pol": 1, "three": [1, 2], "further": [1, 19, 20], "11": [1, 8], "cheetah": 1, "run": [1, 8, 9, 10, 11, 13, 15], "biped": 1, "robot": [1, 2, 5, 6, 20, 23], "The": [1, 2, 3, 5, 6, 8, 10, 11, 17, 18, 19, 20, 22, 23], "proport": 1, "forward": 1, "veloc": [1, 5, 11, 14, 15, 19, 20, 22], "maximum": [1, 15], "speed": 1, "17": 1, "dog": 1, "stand": 1, "focus": [1, 2], "postur": 1, "38": 1, "223": 1, "walk": 1, "coordin": [1, 5], "movement": [1, 8, 10, 13, 17, 18, 20, 22, 23], "trot": 1, "perform": [1, 2, 5], "gait": 1, "combin": 1, "stabil": 1, "fetch": 1, "plai": [1, 5, 6], "involv": [1, 2, 6], "locomot": 1, "object": [1, 5, 6, 20], "interact": [1, 19], "232": 1, "finger": 1, "spin": 1, "rotat": 1, "bodi": 1, "hing": 1, "9": [1, 3], "turn_easi": 1, "align": [1, 5, 20], "tip": 1, "free": [1, 19, 22], "target": [1, 14], "easier": 1, "version": [1, 7, 8, 10, 13, 17, 18, 19, 21, 22], "larger": 1, "12": 1, "turn_hard": 1, "smaller": 1, "difficulti": [1, 23], "fish": [1, 8, 10], "right": [1, 20], "itself": [1, 3], "fluid": 1, "21": [1, 5], "swim": [1, 8, 10], "incorpor": 1, "dynam": [1, 2, 20, 23], "24": 1, "hopper": [1, 5], "One": 1, "leg": 1, "minim": 1, "torso": 1, "height": 1, "4": [1, 5, 6, 7, 9, 11, 15, 22], "15": [1, 5, 14], "hop": 1, "humanoid": 1, "simplifi": 1, "maintain": [1, 5, 19, 23], "67": 1, "specifi": [1, 5, 8, 10, 18], "aim": [1, 2], "high": [1, 3, 14], "horizont": 1, "run_pure_st": 1, "focu": [1, 3], "pure": 1, "state": [1, 15, 19], "55": 1, "humanoid_cmu": 1, "advanc": [1, 5, 6], "cmu": 1, "model": [1, 2], "56": 1, "137": 1, "lqr": 1, "lqr_2_1": 1, "linear": [1, 8, 10, 11, 22], "quadrat": 1, "regul": 1, "mass": 1, "actuat": [1, 2], "posit": [1, 5, 14, 19, 20, 22], "optim": [1, 20], "lqr_6_2": 1, "more": [1, 9, 13, 19, 20, 22, 23], "complex": [1, 2, 3, 5], "manipul": [1, 5, 6, 8, 9], "bring_bal": 1, "bring": 1, "locat": [1, 5], "initi": [1, 5], "variat": [1, 4], "44": 1, "bring_peg": 1, "peg": [1, 6], "insert_bal": 1, "insert": [1, 6], "basket": [1, 5], "insert_peg": 1, "slot": 1, "classic": [1, 4, 20, 23], "invert": 1, "limit": [1, 2, 5], "multipl": [1, 5, 8, 10, 11, 13, 18, 19, 22], "3": [1, 2, 5, 22], "point_mass": 1, "easi": [1, 22, 23], "point": [1, 3, 17, 22], "correspond": 1, "global": 1, "x": [1, 5], "y": [1, 5], "ax": [1, 5, 14], "hard": 1, "random": [1, 5], "gain": [1, 23], "per": [1, 5], "episod": [1, 5, 8, 9, 10, 11, 14, 19, 23], "memoryless": 1, "agent": [1, 2, 3], "quadrup": 1, "four": 1, "78": 1, "escap": 1, "environment": 1, "101": 1, "90": 1, "reacher": [1, 5, 7, 11, 13, 19], "link": [1, 3, 5], "sphere": 1, "stacker": 1, "stack_2": 1, "stack": [1, 9], "box": [1, 4, 6, 11, 20, 23], "correct": [1, 14], "placement": 1, "gripper": 1, "49": 1, "stack_4": 1, "63": 1, "swimmer": 1, "swimmer6": 1, "six": 1, "nose": 1, "insid": 1, "25": [1, 3, 5, 15], "swimmer15": 1, "fifteen": 1, "extend": 1, "14": 1, "61": 1, "walker": [1, 5], "trajectori": [1, 3, 7, 8, 10, 11, 13, 14, 19, 20, 22, 23], "horizon": [1, 3, 5, 6, 7], "dimens": [1, 3, 5, 6, 7, 22], "context": [1, 3, 5, 6, 11, 19, 20, 22], "dm_control_prodmp": 1, "A": [1, 3, 5, 6, 7, 10, 22], "promp": [1, 7, 8, 10, 11, 13, 17, 18, 19, 20, 22, 23], "wrap": [1, 7], "1000": [1, 8, 9, 10, 11, 19, 23], "10": [1, 8, 9, 10, 11, 13, 23], "dm_control_dmp": [1, 19], "dmp": [1, 3, 6, 8, 9, 10, 11, 17, 18, 19, 20, 22, 23], "fanci": [2, 3, 5, 9, 11, 19], "provid": [2, 3, 5, 7, 8, 10, 11, 17, 18, 19, 21], "access": [2, 19, 22, 23], "rang": [2, 5, 8, 9, 10, 11, 13, 15, 19, 22, 23], "environ": [2, 4, 8, 9, 10, 11, 13, 14, 15, 17, 18, 20, 21], "air": 2, "hockei": 2, "close": [2, 5, 6, 8, 10, 11, 15], "gap": 2, "between": [2, 5, 14, 19], "simul": [2, 3, 6], "learn": [2, 3, 5, 6, 11, 19, 20, 23], "real": [2, 14], "world": [2, 10], "applic": 2, "variou": [2, 5, 23], "aspect": 2, "oper": [2, 20], "deal": 2, "disturb": 2, "nois": 2, "safeti": 2, "avail": [2, 5, 19, 22], "through": [2, 11], "allow": [2, 3, 8, 10, 11, 17, 18, 19, 22], "develop": 2, "capabl": [2, 5], "differ": [2, 5, 8, 10, 14, 18, 20], "level": [2, 19], "includ": [2, 5, 9, 17, 18, 23], "hit": [2, 5], "defend": 2, "both": [2, 22, 23], "degre": [2, 5, 23], "freedom": [2, 5], "dof": [2, 5], "seven": [2, 5], "7": [2, 5], "configur": [2, 5, 17, 18, 22], "base": [2, 4, 8, 9, 10, 11, 13, 15, 17, 18, 20, 22, 23], "kuka": 2, "iiwa14": 2, "which": [2, 3, 5, 8, 10, 11, 13, 17], "repres": [2, 20, 22], "higher": [2, 23], "control": [2, 4, 19, 20, 22, 23], "akin": 2, "set": [2, 8, 9, 10, 17, 19, 20, 23], "particip": 2, "strategi": 2, "enabl": [2, 11, 19], "react": 2, "adapt": [2, 4, 5], "within": [2, 5], "final": [2, 5], "phase": 2, "tournament": 2, "test": [2, 19, 21], "comprehens": [2, 5, 23], "game": [2, 5, 6], "scenario": 2, "top": [2, 5, 6], "team": 2, "actual": 2, "system": [2, 5], "For": [2, 5, 8, 10, 13, 22], "detail": [2, 19, 22], "inform": [2, 5, 13, 14, 19], "rule": 2, "stage": 2, "submiss": [2, 23], "pleas": [2, 14, 18, 22], "visit": 2, "offici": 2, "websit": 2, "follow": [2, 5, 8, 10, 11, 22], "7dof": 2, "3dof": 2, "airhockit2023": 2, "foundat": [3, 5, 21, 23], "platform": 3, "explor": [3, 23], "experi": 3, "rl": [3, 5, 23], "algorithm": [3, 5], "design": [3, 4, 5, 6, 20], "simpl": 3, "research": [3, 5, 23], "practition": 3, "fundament": 3, "principl": 3, "without": [3, 19, 22], "dimension": [3, 22], "physic": [3, 8], "simplereach": 3, "reach": [3, 5, 6, 19], "ani": [3, 9, 17, 18, 19], "until": 3, "150": [3, 6], "time": [3, 5, 8, 10, 11, 19, 23], "thi": [3, 5, 6, 8, 9, 10, 11, 14, 19, 20, 22, 23], "space": [3, 5, 11, 20, 22], "precis": [3, 5], "toward": 3, "end": [3, 5], "200": [3, 5, 9], "longsimplereach": 3, "18": [3, 5], "viapointreach": 3, "leverag": [3, 9], "support": [3, 6, 10, 19, 20, 22, 23], "self": [3, 22], "collis": 3, "detect": 3, "onli": [3, 5, 8, 10, 17, 19, 21, 22], "100": [3, 5, 7, 15], "199": 3, "viapoint": 3, "respect": 3, "holereach": [3, 9, 11], "effector": [3, 5], "need": [3, 5, 8, 10, 18, 22], "narrow": 3, "hole": [3, 6], "colld": 3, "wall": [3, 6], "fancy_dmp": [3, 5, 11], "holereacherfixedgo": 3, "fix": [3, 5, 10], "attractor": 3, "30": 3, "add": [4, 8, 10, 19, 22], "coupl": 4, "new": [4, 11, 18, 19, 20, 23], "some": [4, 11, 14, 19], "exist": [4, 6, 8, 10, 11, 17, 18, 19, 22], "while": [4, 5, 15, 19, 20], "other": [4, 8, 10, 19, 22, 23], "were": 4, "build": [4, 22], "u": 4, "from": [4, 5, 6, 8, 9, 10, 14, 19, 20, 22, 23], "ground": [4, 5], "push": [4, 6, 23], "boxpushingdens": [4, 5, 15, 23], "mujoco": [4, 9, 11, 15, 21, 23], "step": [4, 8, 9, 10, 11, 13, 14, 15, 17, 18, 20, 22, 23], "tabl": [4, 23], "tenni": [4, 23], "beer": 4, "pong": 4, "mp": [4, 8, 10, 11, 14, 17, 18, 19, 20, 23], "airhockei": [4, 23], "present": [5, 20, 23], "reinforc": [5, 6, 23], "util": 5, "versatil": 5, "franka": 5, "emika": 5, "panda": [5, 23], "arm": [5, 6], "boast": 5, "orient": 5, "defin": [5, 11, 18, 22], "its": [5, 10], "constrain": 5, "certain": 5, "along": 5, "encompass": 5, "full": [5, 8, 10, 11, 13, 19, 22, 23], "360": 5, "z": 5, "axi": [5, 14], "": [5, 20, 23], "mission": 5, "accuraci": 5, "centimet": 5, "0": [5, 8, 9, 10, 11, 13, 14, 15, 19, 22], "radian": 5, "sine": 5, "cosin": 5, "valu": [5, 9, 14, 19], "angl": 5, "quaternion": 5, "describ": 5, "each": [5, 19], "composit": 5, "function": [5, 9, 11], "serv": 5, "metric": 5, "It": [5, 8, 10, 11, 22], "account": 5, "distanc": 5, "rod": 5, "desir": [5, 15], "penalti": 5, "violat": 5, "well": [5, 19, 22], "cost": 5, "energi": 5, "expenditur": 5, "structur": [5, 6, 8, 10, 11], "purposefulli": 5, "enhanc": [5, 20], "gener": [5, 11, 15, 19, 20, 22, 23], "tempor": 5, "last": [5, 11], "timestep": 5, "spatial": 5, "almost": 5, "enought": 5, "somewhat": 5, "correctli": 5, "custom": [5, 8, 9, 10, 11, 15, 18, 19, 22, 23], "dens": 5, "13": 5, "boxpushingtemporalspars": [5, 11], "boxpushingtemporalspatialspars": 5, "offer": [5, 23], "equip": [5, 6], "respond": 5, "incom": 5, "return": [5, 8, 9, 10, 11, 12, 13, 19, 22], "accur": 5, "oppon": 5, "side": [5, 6], "meter": 5, "65": 5, "compris": [5, 6], "decis": 5, "consid": 5, "successfulli": 5, "complet": [5, 20], "land": 5, "also": [5, 6, 8, 9, 10, 11, 17, 18, 19, 21], "tight": 5, "margin": 5, "20": [5, 11], "reflect": 5, "condit": [5, 15], "whether": [5, 17, 22, 23], "wa": 5, "proxim": 5, "cater": 5, "addit": [5, 17, 18, 19], "overcom": 5, "tabletennis2d": 5, "2d": 5, "350": 5, "19": 5, "tabletennis2dreplan": 5, "replan": [5, 11, 19, 23], "tabletennis4d": [5, 11, 12], "4d": 5, "22": 5, "tabletennis4dreplan": [5, 11], "tabletenniswind": 5, "wind": 5, "effect": [5, 22], "tabletennisgoalswitch": 5, "switch": 5, "tabletenniswindreplan": [5, 11], "upon": [5, 23], "throw": 5, "place": [5, 6], "larg": 5, "establish": 5, "42": [5, 18], "05": [5, 14], "angular": 5, "rel": [5, 22], "bottom": 5, "current": [5, 6, 8, 10, 19, 20, 22], "method": [5, 8, 10, 11, 20, 23], "paramet": [5, 8, 10, 11, 18, 22, 23], "expand": 5, "weight": 5, "basi": [5, 11, 20], "durat": 5, "releas": 5, "implement": [5, 11, 19, 22], "form": 5, "squar": 5, "sum": [5, 11], "across": 5, "penal": 5, "excess": 5, "forc": 5, "encourag": [5, 23], "effici": [5, 6], "t": [5, 11, 14, 15], "befor": 5, "non": [5, 18], "markovian": 5, "contact": 5, "touch": 5, "ha": [5, 8, 10, 21, 22], "made": 5, "compon": [5, 6], "assess": 5, "chosen": [5, 20], "ensur": 5, "fall": 5, "reason": 5, "overal": 5, "specif": [5, 13, 20], "success": 5, "determin": [5, 22], "conclus": 5, "showcas": 5, "abil": 5, "predict": [5, 20], "execut": [5, 11, 19, 20, 23], "popular": 5, "parti": [5, 21], "beerpong": 5, "300": 5, "29": 5, "beerpongstepbas": 5, "beerpongfixedreleas": 5, "modifi": 5, "gymnasium": [5, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 22, 23], "v2": [5, 6, 7, 9, 10, 13, 19], "reacherspars": 5, "same": [5, 8, 10, 11, 17, 18, 19, 22], "longreach": 5, "27": 5, "longreacherspars": 5, "reacher5d": [5, 9, 11, 14, 19], "env": [5, 6, 8, 9, 10, 11, 14, 15, 17, 18, 19, 22, 23], "reacherenv": 5, "reacher5dspars": 5, "reacher7d": 5, "reacher7dspars": 5, "hopperjumpspars": 5, "jump": 5, "250": [5, 8], "16": [5, 9], "hopperjump": 5, "continu": 5, "antjump": 5, "ant": 5, "119": 5, "halfcheetahjump": 5, "halfcheetah": [5, 9], "112": 5, "hopperjumponbox": 5, "hopperthrow": 5, "hopperthrowinbasket": 5, "walker2djump": 5, "walker2d": 5, "depend": [5, 20, 21], "most": 5, "variant": [5, 6, 19, 23], "refer": [5, 6, 7], "fancy_promp": [5, 11, 12, 14, 19, 23], "fancy_prodmp": [5, 11, 12, 15], "dial": 6, "turn": [6, 19], "open": [6, 19, 22], "sourc": [6, 17, 18], "benchmark": [6, 23], "meta": [6, 10], "multi": 6, "50": [6, 7], "divers": 6, "featur": 6, "univers": 6, "tabletop": 6, "sawyer": 6, "varieti": [6, 11], "everydai": 6, "share": 6, "pivot": 6, "reus": 6, "acquir": 6, "relat": 6, "make": [6, 8, 9, 10, 11, 12, 13, 14, 15, 19, 22, 23], "ml1": [6, 19], "standard": [6, 8, 10, 23], "assembli": 6, "assembl": 6, "39": 6, "basketbal": 6, "bin": 6, "pick": [6, 18], "button": [6, 10], "press": [6, 10], "topdown": 6, "down": 6, "perspect": 6, "coffe": 6, "machin": 6, "pull": 6, "lever": 6, "disassembl": 6, "door": 6, "lock": 6, "unlock": 6, "hand": [6, 22], "drawer": 6, "faucet": 6, "hammer": 6, "handl": [6, 14], "out": [6, 23], "back": [6, 11], "backward": 6, "plate": 6, "slide": 6, "unplug": 6, "soccer": 6, "stick": 6, "against": 6, "shelf": 6, "sweep": 6, "contain": 6, "window": 6, "metaworld_promp": [6, 10], "metaworld_prodmp": [6, 19], "now": [6, 10, 11], "lunar": 7, "lander": 7, "lunarland": 7, "we": [7, 8, 10, 11, 18, 19, 20, 21, 22, 23], "farama": [7, 21], "previous": 7, "openai": [7, 9, 19, 23], "doc": 7, "overview": 7, "counterpart": 7, "gym_promp": [7, 13, 19], "continuousmountaincar": 7, "fetchslidedens": 7, "v1": [7, 9, 10], "fetchreachdens": 7, "import": [8, 9, 10, 11, 12, 13, 14, 15, 19, 22, 23], "def": [8, 9, 10, 11, 12, 13, 15, 22], "example_dmc": 8, "env_id": [8, 9, 10, 11, 13, 14, 15], "seed": [8, 9, 10, 11, 13, 14, 15, 19], "iter": [8, 9, 10, 11, 15], "render": [8, 9, 10, 11, 13, 14, 15, 19, 23], "true": [8, 9, 10, 11, 12, 13, 14, 15, 17, 19], "dmc": [8, 9, 21, 23], "domain_nam": [8, 9], "task_nam": [8, 9, 10], "environment_nam": [8, 9], "arg": [8, 9, 10, 11, 13, 17, 18], "either": [8, 9, 14], "determinist": [8, 9, 10, 11], "behaviour": [8, 9, 10, 11], "number": [8, 9, 10, 11, 13, 15, 19, 22], "rollout": [8, 9, 10, 11], "ob": [8, 9, 10, 11, 13, 15], "reset": [8, 9, 10, 11, 13, 14, 15, 19, 22, 23], "print": [8, 9, 10, 11, 13, 17, 19, 22], "shape": [8, 9, 10, 14, 22], "observation_spac": [8, 9, 10, 22], "action_spac": [8, 9, 10, 11, 13, 14, 15, 19, 22, 23], "ac": [8, 10, 11, 13, 15, 22], "sampl": [8, 9, 10, 11, 13, 14, 15, 19, 22, 23], "mode": [8, 10, 11, 13, 14, 15, 19], "human": [8, 10, 11, 13, 15, 19, 23], "termin": [8, 9, 10, 11, 13, 15, 19, 22, 23], "truncat": [8, 9, 10, 11, 13, 15, 19, 22, 23], "info": [8, 9, 10, 11, 13, 15, 19, 22, 23], "del": [8, 10, 15], "example_custom_dmc_and_mp": 8, "alreadi": [8, 10, 11, 13, 17, 18, 19, 22], "regist": [8, 10, 11, 13, 15, 18, 22, 23], "henc": [8, 10, 11, 19], "adjust": [8, 10, 11], "hyperparamet": [8, 10, 11], "yet": [8, 10, 11, 21, 22], "recommend": [8, 10, 11, 22, 23], "abov": [8, 9, 10, 11, 19], "you": [8, 10, 11, 17, 18, 19, 21, 22, 23], "just": [8, 10, 11, 19], "interest": [8, 10, 11], "chain": [8, 10], "those": [8, 10, 11, 21], "appreci": [8, 10, 11, 23], "pr": [8, 10, 11, 22, 23], "especi": [8, 10, 11], "repo": [8, 10, 11], "http": [8, 10, 11, 21, 23], "github": [8, 10, 11, 21, 23], "com": [8, 10, 11, 21, 23], "alrhub": [8, 10, 11, 21, 23], "accord": [8, 10], "base_env_id": [8, 10, 11, 15], "replac": [8, 10], "your": [8, 10, 14, 22, 23], "inherit": [8, 10], "rawinterfacewrapp": [8, 10, 17, 18, 22], "can": [8, 10, 11, 15, 17, 18, 19, 21, 22, 23], "case": [8, 10, 19, 22], "thei": [8, 10, 11, 20, 21], "suit": [8, 20, 23], "mpwrapper": [8, 10, 11, 15], "trajectory_generator_kwarg": [8, 10, 11, 15], "trajectory_generator_typ": [8, 10, 11, 15], "phase_generator_kwarg": [8, 10, 11, 15, 22], "phase_generator_typ": [8, 10, 11, 15, 22], "controller_kwarg": [8, 10, 11, 14, 15, 22], "controller_typ": [8, 10, 11, 15], "motor": 8, "p_gain": [8, 14, 22], "d_gain": [8, 14, 22], "basis_generator_kwarg": [8, 10, 11, 15, 22], "basis_generator_typ": [8, 10, 11, 15], "zero_rbf": [8, 10, 11], "num_basi": [8, 10, 11, 15, 22], "num_basis_zero_start": [8, 10, 11, 22], "exp": [8, 10, 11, 15], "alpha_phas": [8, 10, 11], "rbf": [8, 10, 11], "make_bb": [8, 10, 15], "black_box_kwarg": [8, 10, 15], "traj_gen_kwarg": [8, 10, 15], "phase_kwarg": [8, 10, 15], "basis_kwarg": [8, 10, 15], "call": [8, 10, 19], "onc": [8, 10, 19, 20], "begin": [8, 10, 19], "everi": [8, 10, 11, 19, 20], "consecut": [8, 10], "none": [8, 10, 11, 17, 18, 19], "possibl": [8, 10, 11], "chang": [8, 10, 11, 19, 22], "nth": [8, 10], "should": [8, 10, 18, 22], "displai": [8, 10], "__name__": [8, 9, 10, 11, 12, 13, 15], "__main__": [8, 9, 10, 11, 12, 13, 15], "disclaim": [8, 10], "afterward": [8, 10], "doe": [8, 10], "affect": [8, 10], "underli": [8, 10, 19], "export": [8, 10], "mujoco_gl": 8, "osmesa": 8, "vision": 8, "integr": [8, 22, 23], "yield": 8, "error": 8, "reach_site_featur": 8, "hybrid": [8, 10, 19], "framework": [8, 9, 10, 20, 22, 23], "dm_control_promp": 8, "becaus": [8, 10], "longer": [8, 19], "combo": 8, "collect": [9, 14, 19, 23], "defaultdict": 9, "numpi": [9, 14, 22], "np": [9, 14, 22], "example_gener": 9, "make_env": 9, "id": [9, 15, 17, 18, 19, 22], "example_async": 9, "n_cpu": 9, "int": [9, 22], "533d": 9, "n_sampl": 9, "800": 9, "vector": 9, "multiprocess": 9, "faster": 9, "Be": 9, "awar": 9, "reduc": 9, "total": [9, 19], "length": [9, 19], "individu": [9, 20], "cpu": 9, "core": 9, "parallel": 9, "tupl": [9, 22], "done": [9, 15], "type": [9, 17, 18, 19, 22], "ndarrai": [9, 22], "asyncvectorenv": 9, "make_rank": 9, "OR": 9, "plot": [9, 12, 14], "zero": [9, 14], "buffer": 9, "list": [9, 17, 18, 19], "would": 9, "than": 9, "request": 9, "num_env": 9, "repeat": 9, "ceil": 9, "append": 9, "f": [9, 14], "do": [9, 22], "threshold": 9, "map": 9, "lambda": [9, 15], "v": 9, "basic": [9, 10, 23], "example_meta": 10, "alwai": [10, 19], "found": [10, 19, 20, 23], "here": [10, 11, 19, 20, 22, 23], "arxiv": 10, "org": 10, "pdf": 10, "1910": 10, "10897": 10, "io": 10, "todo": [10, 14], "work": [10, 14, 19], "due": 10, "issu": [10, 19], "code": 10, "TO": 10, "BE": 10, "fals": [10, 11, 15, 17], "FOR": 10, "THE": 10, "remov": 10, "example_custom_meta_and_mp": 10, "goal_object_change_mp_wrapp": 10, "rais": [10, 19, 22], "valueerror": 10, "bug": 10, "temporari": 10, "workaround": 10, "alter": [10, 11], "mujocoenv": 10, "offscreen": 10, "mai": 10, "behavior": 10, "might": [10, 14], "necessari": [10, 19, 22], "opengl": 10, "ld_preload": 10, "usr": 10, "lib": 10, "x86_64": 10, "linux": 10, "gnu": 10, "libglew": 10, "so": [10, 22], "500": [10, 11], "buttonpress": 10, "example_mp": [11, 13], "env_nam": [11, 13, 15], "black": [11, 20, 23], "equival": 11, "have": [11, 20, 21, 22], "creat": [11, 17, 19, 23], "take": 11, "care": 11, "extern": 11, "render_mod": [11, 23], "els": [11, 13], "raw": [11, 17, 18], "parametr": [11, 20], "give": 11, "sub": [11, 19], "equal": 11, "default": [11, 17, 18, 19, 22], "over": 11, "wise": [11, 19], "aggreg": 11, "example_custom_mp": 11, "argument": [11, 17, 19], "mp_config_overrid": [11, 14, 17, 18], "wai": [11, 14, 19], "mani": 11, "class": [11, 17, 18, 22], "custom_mpwrapp": 11, "mp_config": [11, 22], "weights_scal": [11, 15], "example_fully_custom_mp": 11, "custom_env_id": 11, "custom_env_id_dmp": 11, "custom_env_id_promp": 11, "upgrad": [11, 17, 22, 23], "mp_wrapper": [11, 15, 17, 18, 22], "add_mp_typ": [11, 17, 18], "base_id": [11, 18], "try": [11, 19, 23], "don": 11, "correlcti": 11, "except": [11, 19], "pass": [11, 17], "example_fully_custom_mp_altern": 11, "instead": [11, 17, 18, 20, 22], "mp_arg": 11, "dure": 11, "registr": [11, 18], "main": 11, "prodmp": [11, 15, 17, 18, 19, 20, 22, 23], "boxpushingdensereplan": [11, 15], "obs1": 11, "compare_bases_shap": 12, "env1_id": 12, "env2_id": 12, "env1": 12, "traj_gen": [12, 13], "show_scaled_basi": 12, "env2": 12, "stuff": 13, "look": [13, 19, 22], "boolean": [13, 22], "ordereddict": 14, "matplotlib": 14, "pyplot": 14, "plt": 14, "howev": [14, 19, 22], "verifi": 14, "extract": 14, "below": 14, "w": 14, "po": [14, 15], "vel": [14, 15], "get_trajectori": 14, "base_shap": 14, "actual_po": 14, "len": 14, "actual_vel": 14, "act": 14, "ion": 14, "fig": 14, "figur": 14, "add_subplot": 14, "img": 14, "imshow": 14, "rgb_arrai": 14, "show": [14, 19], "des_po": 14, "des_vel": 14, "enumer": 14, "zip": 14, "tracking_control": 14, "get_act": 14, "current_po": [14, 22], "current_vel": [14, 22], "clip": 14, "low": 14, "set_data": 14, "canva": 14, "draw": 14, "flush_ev": 14, "figsiz": 14, "subplot": 14, "131": 14, "titl": [14, 23], "p1": 14, "c": 14, "c0": 14, "label": 14, "p2": 14, "c1": 14, "xlabel": 14, "gca": 14, "get_legend_handles_label": 14, "by_label": 14, "legend": 14, "kei": [14, 19], "132": 14, "133": 14, "std": 14, "example_run_replanning_env": 15, "example_custom_replanning_env": 15, "box_push": 15, "max_planning_tim": 15, "plan": 15, "replanning_schedul": 15, "trigger": 15, "condition_on_desir": 15, "boundari": [15, 23], "next": 15, "str": [17, 18], "entry_point": [17, 22], "union": [17, 22], "callabl": 17, "black_box": [17, 18], "raw_interface_wrapp": [17, 18], "registri": [17, 18], "defaultmpwrapp": [17, 18], "register_step_bas": 17, "bool": [17, 22], "dict": [17, 18], "kwarg": 17, "If": [17, 19, 21, 22, 23], "want": [17, 21, 23], "uniqu": [17, 18, 20], "identifi": [17, 18], "entri": 17, "srtep": 17, "dictionari": [17, 18, 19], "overrid": [17, 18], "keyword": 17, "constructor": 17, "note": [17, 18], "otherwis": [17, 18], "given": [17, 19, 22], "string": 17, "notat": 17, "warn": 17, "messag": 17, "suggest": 17, "exampl": [17, 18, 19, 22], "To": [17, 18, 19, 23], "myenv": [17, 18], "myenvclass": 17, "my_modul": 17, "expect": 18, "known_mp": 18, "Will": [18, 23], "match": [18, 22], "wish": 18, "one": [18, 22, 23], "alongsid": 18, "custommpwrapp": 18, "param": [18, 23], "prepar": 19, "ad": 19, "namespac": 19, "legaci": [19, 21], "metaworld": [19, 20, 21, 23], "n": 19, "cumul": 19, "part": [19, 22], "mainli": 19, "meant": 19, "debug": 19, "log": 19, "train": 19, "step_act": 19, "output": 19, "step_observ": 19, "intermedi": 19, "step_reward": 19, "trajectory_length": 19, "origin": 19, "In": [19, 22], "miss": 19, "fill": 19, "_": 19, "keep": 19, "mind": 19, "process": 19, "split": 19, "lean": 19, "still": [19, 22], "beta": 19, "feel": [19, 22], "problem": 19, "occur": 19, "directli": [19, 22], "gym_": 19, "again": 19, "conveni": 19, "variabl": 19, "store": 19, "all_movement_primitive_environ": 19, "all_fancy_movement_primitive_environ": 19, "all_gym_movement_primitive_environ": 19, "deepmind": [19, 23], "all_dmc_movement_primitive_environ": 19, "all_metaworld_movement_primitive_environ": 19, "movement_primitive_environments_for_n": 19, "my_custom_namespac": 19, "tradit": 20, "concept": 20, "stochast": 20, "search": 20, "commonli": 20, "produc": 20, "like": [20, 21], "probabilist": [20, 23], "convert": 20, "track": 20, "pd": [20, 23], "tailor": 20, "addition": 20, "special": 20, "overarch": 20, "remain": 20, "polici": 20, "craft": 20, "accommod": 20, "contextu": [20, 22], "At": 20, "onset": 20, "subset": 20, "demand": 20, "virtual": 21, "venv": 21, "3rd": 21, "altern": [21, 23], "poetri": 21, "conda": 21, "few": 21, "choos": 21, "box2d": 21, "jax": 21, "automat": 21, "date": 21, "sinc": 21, "git": 21, "d155d0051630bb365ea6a824e02c66c068947439": 21, "egg": 21, "clone": 21, "repositori": 21, "go": 21, "folder": 21, "cd": 21, "manual": 21, "guid": 22, "explain": 22, "how": 22, "abc": 22, "abstractmethod": 22, "properti": 22, "context_mask": 22, "mask": 22, "filter": 22, "unwant": 22, "unnecessari": 22, "after": 22, "first": 22, "receiv": 22, "arrai": 22, "indic": 22, "ones": 22, "dtype": 22, "float": 22, "exclus": 22, "regardless": 22, "indirectli": 22, "notimplementederror": 22, "overitten": 22, "attribut": 22, "document": 22, "mp_pytorch": 22, "userguid": 22, "anoth": 22, "merg": 22, "num_basis_zero_go": 22, "rough": 22, "outlin": 22, "shown": 22, "simpli": 22, "cool_new_env": 22, "my_custom_mpwrapp": 22, "my_custom_env": 22, "custom_prodmp": 22, "built": 23, "fork": 23, "renown": 23, "librari": 23, "sever": 23, "etc": 23, "With": 23, "straightforward": 23, "transform": 23, "compat": 23, "contribut": 23, "own": 23, "re": 23, "inspir": 23, "assist": 23, "highli": 23, "randomli": 23, "sleep": 23, "metadata": 23, "render_fp": 23, "about": 23, "pypi": 23, "master": 23, "what": 23, "usag": 23, "tune": 23, "public": 23, "softwar": 23, "author": 23, "otto": 23, "fabian": 23, "celik": 23, "onur": 23, "roth": 23, "dominik": 23, "zhou": 23, "hongyi": 23, "abstract": 23, "unifi": 23, "approach": 23, "url": 23, "organ": 23, "autonom": 23, "lab": 23, "alr": 23, "kit": 23}, "objects": {"fancy_gym": [[16, 0, 0, "-", "envs"], [17, 1, 1, "", "register"], [18, 1, 1, "", "upgrade"]]}, "objtypes": {"0": "py:module", "1": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "function", "Python function"]}, "titleterms": {"api": [0, 23], "deepmind": [1, 8], "control": [1, 3, 8, 14], "dmc": 1, "step": [1, 3, 5, 6, 7, 19], "base": [1, 3, 5, 6, 7, 19], "environ": [1, 3, 5, 6, 7, 19, 22, 23], "mp": [1, 3, 5, 6, 7, 12, 22], "airhockei": 2, "classic": 3, "fanci": [4, 23], "mujoco": 5, "box": [5, 19], "push": 5, "tabl": 5, "tenni": 5, "beer": 5, "pong": 5, "variat": 5, "exist": 5, "metaworld": [6, 10], "gymnasium": 7, "exampl": [8, 9, 10, 11, 12, 13, 14, 15, 23], "gener": 9, "usag": [9, 19], "movement": 11, "primit": 11, "param": 12, "tune": [12, 14], "openai": 13, "env": [13, 16], "pd": 14, "gain": 14, "replan": 15, "fancy_gym": [16, 17, 18], "regist": 17, "upgrad": 18, "basic": 19, "black": 19, "what": 20, "i": 20, "episod": 20, "rl": 20, "instal": 21, "from": 21, "pypi": 21, "recommend": 21, "master": 21, "creat": 22, "new": 22, "gym": 23, "kei": 23, "featur": 23, "quickstart": 23, "guid": 23, "user": 23, "cite": 23, "project": 23, "icon": 23, "attribut": 23}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.viewcode": 1, "sphinx": 57}, "alltitles": {"API": [[0, "api"], [23, null]], "DeepMind Control (DMC)": [[1, "deepmind-control-dmc"]], "Step-Based Environments": [[1, "step-based-environments"], [3, "step-based-environments"], [5, "step-based-environments"], [6, "step-based-environments"], [7, "step-based-environments"], [19, "step-based-environments"]], "MP Environments": [[1, "mp-environments"], [3, "mp-environments"], [5, "mp-environments"], [6, "mp-environments"], [7, "mp-environments"]], "AirHockey": [[2, "airhockey"]], "Classic Control": [[3, "classic-control"]], "Fancy": [[4, "fancy"]], "Mujoco": [[5, "mujoco"]], "Box Pushing": [[5, "box-pushing"]], "Table Tennis": [[5, "table-tennis"]], "Beer Pong": [[5, "beer-pong"]], "Variations of existing environments": [[5, "variations-of-existing-environments"]], "Metaworld": [[6, "metaworld"]], "Gymnasium": [[7, "gymnasium"]], "DeepMind Control Examples": [[8, "deepmind-control-examples"]], "General Usage Examples": [[9, "general-usage-examples"]], "Metaworld Examples": [[10, "metaworld-examples"]], "Movement Primitives Examples": [[11, "movement-primitives-examples"]], "MP Params Tuning Example": [[12, "mp-params-tuning-example"]], "OpenAI Envs Examples": [[13, "openai-envs-examples"]], "PD Control Gain Tuning Example": [[14, "pd-control-gain-tuning-example"]], "Replanning Example": [[15, "replanning-example"]], "fancy_gym.envs": [[16, "module-fancy_gym.envs"]], "fancy_gym.register": [[17, "fancy-gym-register"]], "fancy_gym.upgrade": [[18, "fancy-gym-upgrade"]], "Basic Usage": [[19, "basic-usage"]], "Black-Box Environments": [[19, "black-box-environments"]], "What is Episodic RL?": [[20, "what-is-episodic-rl"]], "Installation": [[21, "installation"]], "Installation from PyPI (recommended)": [[21, "installation-from-pypi-recommended"]], "Installation from master": [[21, "installation-from-master"]], "Creating new MP Environments": [[22, "creating-new-mp-environments"]], "Fancy Gym": [[23, "fancy-gym"]], "Key Features": [[23, "key-features"]], "Quickstart Guide": [[23, "quickstart-guide"]], "User Guide": [[23, null]], "Environments": [[23, null]], "Examples": [[23, null]], "Citing the Project": [[23, "citing-the-project"]], "Icon Attribution": [[23, "icon-attribution"]]}, "indexentries": {"fancy_gym.envs": [[16, "module-fancy_gym.envs"]], "module": [[16, "module-fancy_gym.envs"]], "register() (in module fancy_gym)": [[17, "fancy_gym.register"]], "upgrade() (in module fancy_gym)": [[18, "fancy_gym.upgrade"]]}})
\ No newline at end of file
diff --git a/docs/source/envs/fancy/airhockey.rst b/docs/source/envs/fancy/airhockey.rst
index 9a89ca9..7b9b46b 100644
--- a/docs/source/envs/fancy/airhockey.rst
+++ b/docs/source/envs/fancy/airhockey.rst
@@ -1,7 +1,7 @@
 AirHockey
 =========
 
-Fancy Gym provides access to a range of environments for the Robot Air Hockey Challenge, facilitating research in robot learning. The challenge aims to close the gap between simulated learning and real-world application by focusing on various aspects of robotic operation, such as dealing with disturbances, observation noise, safety, and actuator limitations.
+Fancy Gym provides access to a range of environments for the `Robot Air Hockey Challenge `_. The challenge aims to close the gap between simulated learning and real-world application by focusing on various aspects of robotic operation, such as dealing with disturbances, observation noise, safety, and actuator limitations.
 
 The environments available through Fancy Gym allow for the development of agents capable of performing tasks with different levels of complexity. These tasks include hitting and defending in air hockey with both three degrees of freedom (3 DoF) and seven degrees of freedom (7 DoF) configurations. The 7 DoF tasks are based on the KUKA iiwa14 robot model, which is used in the simulations to represent a higher level of control complexity akin to real-world settings.
 
diff --git a/docs/source/envs/fancy/mujoco.md b/docs/source/envs/fancy/mujoco.md
index c58ded5..018d901 100644
--- a/docs/source/envs/fancy/mujoco.md
+++ b/docs/source/envs/fancy/mujoco.md
@@ -32,7 +32,7 @@ Variations of this environment are available, differing in reward structures and
-The table tennis task offers a dynamic and interactive environment designed for the development and testing of reinforcement learning (RL) systems. Using a robotic arm equipped with seven degrees of freedom (DoFs), the challenge is to respond to incoming balls and return them accurately to a specified goal location on the opponent's side of the table. +The table tennis task offers a robotic arm equipped with seven degrees of freedom (DoFs). The task is to respond to incoming balls and return them accurately to a specified goal location on the opponent's side of the table. The context space for this environment includes the initial ball position, with x-coordinates ranging from -1 to -0.2 meters and y-coordinates from -0.65 to 0.65 meters, and the goal position with x-coordinates between -1.2 to -0.2 meters and y-coordinates from -0.6 to 0.6 meters. The full observation space comprises the sine and cosine values of the joint angles, the joint velocities, and the ball's velocity, providing comprehensive information for the RL system to base its decisions on. @@ -118,4 +118,4 @@ No longer used? ## MP Environments -Many of these envs also exist as MP-variants. Refer to them using `fancy_DMP/` `fancy_ProMP/` or `fancy_ProDMP/`. +Most of these envs also exist as MP-variants. Refer to them using `fancy_DMP/` `fancy_ProMP/` or `fancy_ProDMP/`.