From 4be05440a1b3b66e044be779e4f1c37a564e2583 Mon Sep 17 00:00:00 2001 From: Dominik Roth Date: Tue, 23 Jan 2024 17:46:48 +0100 Subject: [PATCH] Final?! changes to docs --- docs/build/doctrees/environment.pickle | Bin 56764 -> 56764 bytes docs/build/doctrees/envs/fancy/mujoco.doctree | Bin 66003 -> 64540 bytes .../html/_sources/envs/fancy/mujoco.md.txt | 7 ------- docs/build/html/envs/fancy/mujoco.html | 7 ------- docs/build/html/searchindex.js | 2 +- docs/source/envs/fancy/mujoco.md | 7 ------- 6 files changed, 1 insertion(+), 22 deletions(-) diff --git a/docs/build/doctrees/environment.pickle b/docs/build/doctrees/environment.pickle index 43e6647435b75f1d0a866701ef82e06a5226ed48..24c61da0c5040a40c4cc75fc03bbd8e20d04bc52 100644 GIT binary patch delta 3511 zcmZ8k4Nz3q73M8OB!k2SiXjOG*q4Mqmp}PYl!B0S5dp$JnvwoF{L)9cK1? z-*@kQ@7#CJx#x1`bmW=SktfykMX^rzCSR_{>vT8UU8+CUxy9b$ZFl-|9UZNzKZZv; zoLzR+Z)UvC?r!bL?dTSsRu9lmu)&lZ9 zQ{NR+M8r=jFKqb1=^y=2Oc_j_{R{E;5Zm&-_?y8F%v8igh%GdUiw1k`A0LYg27A4+ zS9}#>V>RMygB^U(Ca(2`Xi>Ge9AYg`h^ryCFIs#XV(;aOn<4hiPVrZRy%F`X_)Cao z{7PI3vCn$Nn8AiOo)VL$71O&PzBeLn7=wp?GfR9EVz+LK>jpc#?nUukhy}k8;|3eq z5e-)|%A~L1k<3Er8q{Z&NS9$CbAfaf&Sq9YU1mB=q|c7FdVAD>xQXLgN%updOSF?$ z)C_+C?8{7s16hy7&~8X6L?sn2W+h3N;GbF9(ir}xz{2b}Y4Sdr1-|U%(iDtlTfv-@ zP*?kjsE&+?sFk{X9H8y0s6@V9%@9>+>*hr1;}76Ch3x;w>rMK2B#wUtjXBxU73j_R z2;R%Jz`A)3XehM6&3UU~A@UEaQ{Y8w1$;8k0^eF!La@LBO}RgXsUi!U&s`0z^DR)H zw;HnZERfv#6x_T-vU3XgM(TJagYd~xuMENha5Te`{y9rU=i~WQs z=fwyi`gr0vApfWr!}f!O-(&ZEg8{3Bh9R^B*rE5D$y&7R^?ZLHe9YQDTdFQ7GTmO zz(kD=>{T)}ER-Y~*Fl!ABl{z@Gyjch4#wH!~ zt?Xj(X4EPZ&4n^MZf!Nb@XbvgxczK1#P*nBZFz#W`MEUQc#rPipPxtnh>(BFUcl*z z9&%s^raZE?cMVRR@|dBaAxFF3j8l{A4)Z8U#m;u8%p| z!MaoiuQLb-_UPJ${8SiSXM;m~_4#>iLCpU@xH>TZvtZwP8~mtDhCAzn(CKhvEx2Ks zQ--r52#Ce18 zYN!6@n4%PD-e?1tPliu72I2cQ{>uA(F8Ff2ti9~pDj_gy$=!P;c<1LHtfo{b*ldH- z+w_lic(YqV60gne*&{*MVh`3?GFZ3TprKsW4sONo)KIQ}r+;s&VWKtmZkC|7x)|>D z9filAmf@rRAbdKY$M?>T7C1I2YyCT|5(2aK`&~PA(73xtf|qvaj>nZ|LF=FmPVCY@ z*`Ef3VC$eqEQI0GBzRP@L6%$A29+cUfmu7T*U126|CiFZ_JjYjB#pz0K%(~DJ_kZ= zMIgn5#cfY9&4rY9skPKt_iFGCB#6(J@dP&1V3LbO4~C>c=rE zeKb_}XsGDXP{pI6YDYt*j)v+S4HY>Ws_Dt z;R<6L!dOQbQ>IxTFMMg5GJ83Uy%NUW4P(c{*oiQ9GK{?+#y&7uCi(qqgA)5~7&|x3 zw3>r=^{6+g9Cb9*1<+8`(NNUUP}I@T$&ZGjj)tO+hN6y!qK<~5j)tO+hN6y!qK<~5 zj)tO+(ep=n?XFJM52M2+*xv6B*JEq1J!DIv_~SH+KN^ZZ8j3%faX5Ks83$NlhZXi$ zVR!Xgn!?U1?5o1AD(tDkjwba%7QoN$VZ?orHIy#Yf8VnA>)wKb|{dbX-KlfGQqD zBd$W+(Q3S9tUQ|5H*5Q#+NcLX%*DZ4{9Bs&z7)YSx8`ZNZu}t@xl0>j=Uf)KVH@J6 znJjYeHpGDz7P*a2i+y#gcCpGWeOj%nnZqJ?cSG!-!6I+R5I=}!k$b)&ey)q${ta=J zF7i#l5c`t#hw`PsP~XRi7ya_csHFzzDpS5sq7S1 z`CehDm!DvfuNa27BnI-|O2~00^B7+>jIrDCEb^_x5bHCvpS@MK;7M}BAFcnd;#4`W Vy8SWy&sK9=Plwv2`np@J{{^$Fz9j$v delta 3491 zcmZ8k4Nz3q73Kkv(m|RN!WG&=?GO<(KG1y-N?c!#XU3^nqHrU7FRdFNA_P;0oVX#j&sp7W5&R)AL zE*k8dvrl{xWno#|>W|WsN#aVBU3ytuHQ4#MDsd^wvLA?VqHKXzT#qv6Ht|`MZSNQN z4EAaEF7bJkz1bv2;+KxC{zBDO@wG8{;aZ-!X0XpDrir^zHdG?Min1F=#Hhh8hM$5f z)2gK}U~+yLBv|smpPwOJfr0#4(p5N}UoTyPruey=s`(@uE5{ zR0_NEGhwe~N;0j5lrmJN!X+di8>wE6Xaz5pLb(Zygr_Q;}@Z&ut53}HWz+?^B0$x z!9CppXRKzpH+?yLU15fk^Ri&OwHAtS?3Q&I%)_zPqNkvKx*5(FEr;I}o1v+AIXKGA zkm>j(+%K+$NU0gFI%Qa2Qj4FbxFiooN>;;~8D>~nDxj*!3|8?t{H&}NKEzqR?Z^Wa z@y1FsJSgjg0-SN6d^I$enIU;bE8HwM?+NC@kr}n{dwg_!#cH^XQ-v#5zmW-a&-r&bDh8v}l|axM3OXuh)P;KOz6j7s%Mduh(A=zBApQBUgQ#@ z8WvVURKKE{&ARHi~f)DueV_B(i&8n`Bhc}+{!l%kV_=Z0*pKa|ssM%e6^1oTAIA zyWX-+fSU_#u-GL-%c2v~4K1O;5)TdY{8&rraH7!$IrC+0N>iSMz@#-d*XiKUk~STf zT3U6`zpR_VYl%2>2u#r2T&R8eEG~@*xh`Ib zu1DJ`u3^~ekhP&z=(^LPyMEP%u1K_Mdq9G8+)pzdez@(I;g}-=r#(Kb>rU7wWC*w- zSljP=yja^);mjHv{JdI*Vs`{y>e9d4%2EsLUTXtSP=<$VBQU*D*R8?_;Uy+mT{8hr ziwLN5eb@s6?DaBi>x{tOox0zHvO>7-wZZ-&-M7gXf#FttY@mE99QNDbXq!Hk8i>F^ zhY$ND3)D__3R&Lg@w@3_r^g zX$Lm=BqV8CcJEFJUR&?SKFb8_CL5&m>K?Cb!ta&Rn+8jo3$%atEo7oC+q_-^o7ac! zm}hL{`~wl9klG|mEeV~`odBxE#Mfm z!SUzyh5cg^+5;tJ?@I+ke8^e9Pj41Gzg+)$pg zu|LJIb7M?f_{#Ts)>~E1IvP3+&`{RVP}b2<*3r-jfQGV;hO&-^vW|wbj)t<1hO&-^ zvW|wbj)t<1hO&;?3nd2d`lp8A%)Xh@=kWc$COqOB_S>>3|L8{fM??8XL-|KD3Mck2 z<^(Gou)^^w9InFADjclBu__#@!jUQ*sKRk79HzoiDjcN3F)AFQ!VxN5mI@y}3LiWQ zhop$RDHw~w5h)nZ;DHvrsa!fxii;S3unZSbcW}0JPuqO(JxRI+a}L$ueW>rymNY&g zlTzd222}A=G~z0x9-fEyjb(>(`=9gKDZ5Wd@_rCh8yC^4i@=19~1i<7wlk_kM=RO@oYMae99Z*b4e`nat!gNF7nxL zh?B;#Ctm{$(V=_tjld8)-g$&w`Ep>Wztcs&Cm7;-UF0i+A^z|tzC9S?{5+nMFA|3M zehyqaJfSc#o5%P)2S>(HgA#P8GlGi5`4o%`QzGE0;BWW!1b;A(<_?Y&q*Q;ke iPVWsR^#t5qcBf0_Lh1=6^Z!R}?q09jtpz diff --git a/docs/build/doctrees/envs/fancy/mujoco.doctree b/docs/build/doctrees/envs/fancy/mujoco.doctree index 12dd8a40556580c359ed011c756672e5a0e7012f..12330b98ec602d982b108b68e85ab0d94ee0f003 100644 GIT binary patch delta 4168 zcmaKvdsI}{6^A{W*UW$n0|?0cm5)9EG6=M>X;Ik{O528&{Ont?gS{mD|R6`n<(|yjl_s+~}R{l9Kzy12| zKKtA`b9sw*^PrdS3qCtc4~KO4MwWJ7C`$v}U7FoFd;MJob{*zflkrGd2v%+=@UGMi z8G<3Feae!(qwHNev<@E!ojNo{nen#`X1Juo!jZ{vUNcx5=fD?I zyse4cds|g1Jd%d*JPiFfl?}t*Dk}u*we&IL;2rLjXTKBr>q2J}@vGVtNY!K9o+((grGlLkFgXg$DGAdflXOd%{V(>h+ak$LO;=&Q z6Z)X0D=-jj;QeGqG*LOqqrgDC)JJojb-TmNd$|^#HlQgs#qhL3Gt!n`f@gQ{+d8OKtIDG817eqJ}~s9_OUL7||0l@&gH0u(Jw2_s5{-XdK-6I1G4(kY&lP zIPTEhnhZCz$imm2gn$6?ocaLqoJzWryTf6WG>p&;nN3-cCdCPwNV^2b{b_*PpddhS z{#4;y6d*VkNZ0vfq=9k#W+SUaV{<-i5#D;$yAoTP7eQr!Alx8g*nC{_+6;I@mfWl5 zp+RD!v7s{@-j}9#RridhZ0M8P1x84qZ2GvFgx_@XA6u{t*b?n?QNCR?zzEdrcUe#m90r5ft?PeIF3BeovQXQQxY z|9HbQ3TbShAdSYFLn#muD28A`R|s0#qj2)ap?IUifX4QjkP#@_d$HpwI@0b5$k1>s zfu*YnXl7Y4_O@ABkt%5e!K#FzLN)MLOZxA_S)-7D&1DvWg@;q*$kIUM>9F)YKMZ`w zAOCrHA?p&Q7b@&WB>Q2Ju3fSlJNCh47wc7z05WjaOKJdT9Tc_itCGeFMx!`*0W>i5 z?MLYqS{N-2BZYyryYpI(7Q$2X8mHI6A_X$rD2~}QnPw^(>6k6(a=>z<+EFMKA$m1r zIlg+#3`?~L{u%aD&Grm-Uud%D~Q!O-|YHhk+MXF>d7^=g)H1^ELl2`7&U5{E1bdyl68CFbO* zQX8jgDtM06XR5jzch8CSuv%0@=N=uD1c|w|aZj4Jyi;a$_OwEMkZ9_NbD7|9Ig`rw zz0S?~!pUgpkkt-pau)nSN@q05jAKuag=4NV_<9PY-8CGdE#=w8xWIv5=+4$DaC9gDr^ zEqLzIc6c&av~O)+4$N_RlS+Ir-QD}k5m8VgYua3TB0h0B3~Hrb?b0oH{c;pENqwiP z7hdsT?7vb1-LmTJBRV)P8M~x+r(iUGTo3({k&oUjmp7@L@e_CNizlPNDQiA->4{kO zX&8ish<=5Hh)F`bZ-!aYc?QN^ZHLkjZ35Q| zXM^fY7LHir^0pvHL|O7xmu|+YQxR}b>a8x_g1Oh?p-1Z7LWdbt#C1w?uUEruQ5FN= z*RdOd@2?>kmzzR#G%7b7z(Q3*rpM=QS@7R8bljU8IN&3fJK?c0@oRO1G#OC)4hb^q0J>huCQRCR;h^K4iCE4qN5FW-iI<$>si9cK=~ihr!9$M5*!#{n@p#hR(p zJn*(3#0^8Xbdv81Vj%B`uQ#x{*!cBnHl6$vhw|(C8YLnF8~*bzmWMU>^VveOiha_r zRjhevdJrM3!*S+=Nv!01JWf1_Ry=ag_@eVcD%+%bjneWAqXtFWyvmDsi;~=0l!x`- zShac?c=nq-wx;v3L3$0J8`in`zqh=ilgCeRDBbn8@(;4X^lUz1^q67T_$YRiR~S{G zUzO!W^`_@nuU)oub$RK!#8oRx%hwf`IqcqK#^bxAeJE;}jPiHJF)vJXrbYr8zc(rr ztDFhd`v~6N!k2Wur19lPUbMvV#g~4A+r9X5oqqDzKjTX(cNxc*J$%_kOL@J%v~X4N zx{5V~L(^gBS?ff`I+3kTWU3Qc>O_V*5nX32x5e=QPGAeLr|n2*;gO>Ed`pEl7f%Yw9vGGA}TnbfE|GX4kA`eo6sbrX(5T_Aq8H>wqnKkF^bI(n)#91!*1Bu=fFR%mRDFAw>AuHamsClCx{c<6)S zW#L?RtUFF5&UG6bjlwe56LeK^GnS6YSbp71j#cjP`K%Sy{-C2G7$DHfh1DUy(^~H0 zgh3bfXGg6_*y zas|1vgTF{7%Mw*J$f_o4RjrDyO39b2YV7~1syq~=s(wpFSD2?C4JvJNq?)a=nn_wU zo1?2y@@1;I>sq~TN{V4`$#W~(*JS)NLEXFP}kXN zFI!DogRYsgi(sg@8y5E!pRscWyyd28*n9E4Y%llB$Fma+rc$jVFB;%VEpJfb((#EYK6kcdIzn6nFTc$WeAo|&`ra9nOmjJMmsqqA|`eHJzqe|!Yl zooI(V+_h>BRK}yZzR)yFqjtt)>2;N`C>{#}Q-1ZMD(HdTa{Uguej86C=Mj!d!{I0c zA4uquhR!GhpGdeQ4HwA3+L~9-XQ^2Fm>rT6MAfVfS=X@UHL>uV@Q@?P3B^b@teL~c za$g!ryzd1Aj7gwzyk3Tm#C1>FaOc`(>>hM%7>Kv88_Jwf{`Vx{oJ~2vKa#f=!t9=5 zYv0Ub4-?4Bo^l!vV4FyOtf#yWEv$p&Hj-gv0^flmC`zD#-5IW8AL}dcd)WXVNYdjn z$x$Nxa{W^N0&r}Y&VKIc%eC$ecf&ae+1)dOL&CsBngvTDwM%5mXHQ|%#{MuuTI>;v z4LK;>F7=6|!_g>G{|N&YK0X)xiS&4tX`|syq{ddt5GObC4R2c;k2{`7!((el@XtJG zNW`3vvP7E!Dcq>S8}RN;gINP6ZMDNHJxAw+d`x-L0=pznyKd-yemoqJ;#;~XR=oIh z26Rfp$%rA+=h>SVvsg55AAvu=VE~py(ElY*b_r{?JPU)9i1GTCn^>N5Od6b|zV`Xa z=y%9Aj8BMsEAa?E9BdG>9mQ}dk-yJ~nw4P7U+ip>k~uRgCuy#dG-9@h?zoZzOKEUIegabhPHBgK}jnd~Hye5R{5@Y1NT^JMrzH{8nKIh`GLFeHnqg65>iG*7_S zcJ;yHXPs;~cahKDJMS96mQ3Bwl@V7b(}--fd$DFMq%fq@ww7sb{gIh%fPms>8#+E(B>T#^w>0k%dvL=Vt_WiPe zy)w~DvVdpW!f+}Ad*&BW+$ezmu16{0-q^C=&KMqeshGWlXP=+IGD#UA6wuNamSiwH z$-^{99aHpqK7U!a?3Z7;GDtLwSBr4u&uaGp8w0ezSTBDV5%{E)CI?N{D^%y`#m@o7==o z@AVMaQfYS^-xveM(GlDtwl-HqXyXUdQmK)5C|zV4`&NIbl)6*t!vE{HEKn!)rApVn zy|%o)6Sm3~=V^>jNyaD0bE9O;IMM{KO2$J+O5n}t2yPLKuc!#I=66;LbjdY4l`a?` zIocmCN&SM-g@4g83qKg-e439dvSL{>-ttK?h{a_)x4eBT7QE|aqqxTiQ>8{)lt$eg zPR{vh)J@0nMm7VjAKlC5METB0BgSdUSFFkRo4>r(njvKpn1|l)&(`Rs#-1ks2f1vU zZhBfbMK<1lqLLk^)!iED8-TdJSc7{m5kMcbuNxPJrcb5q%S?! zE2G`HDqf7Wy1U}sESKG+8x-emY3R@m8s|Gwe>GTYJa{5+CPp8UM2)77SQ#y5yhp2OTQ98ABxNhL6mj9&k(}MgJg^dbF4hoZ{ z^KH7b=+C$>u7SDIa8JY_`L)wJA2HU&J;h-?Bo4WBSU1hq>fxvI99tS5>AD{p)9FVH zpKj?`_T_VZ;PG^16{F+){Es#6JpbE8Y!-HXdk9|PRr2F~t>(Um*UuCE^xbE0ShnKq z_aotbYQpo#~%v10%7kmZpON!S+P87wTvpen8O~xThe Beer Pong task is based upon a robotic system with seven Degrees of Freedom (DoF), challenging the robot to throw a ball into a cup placed on a large table. The environment’s context is established by the cup’s location, defined within a range of x-coordinates from -1.42 to 1.42 meters and y-coordinates from -4.05 to -1.25 meters.

The observation space includes the cosine and sine of the robot’s joint angles, the angular velocities, and distances of the ball relative to the top and bottom of the cup, along with the cup’s position and the current timestep. The action space for the robot is defined by the torques applied to each joint. For episode-based methods, the parameter space is expanded to 15 dimensions, which includes two weights for the basis functions per joint and the duration of the throw, namely the ball release time.

Action penalties are implemented in the form of squared torque sums applied across all joints, penalizing excessive force and encouraging efficient motion. The reward function at each timestep t before the final timestep T penalizes the action penalty, while at t=T, a non-Markovian reward based on the ball’s position relative to the cup and the action penalty is considered.

-

Conditions for the task are specified as follows:

-
    -

  • The ball contacts the ground before touching the table.

    • -

  • The ball is not in the cup and has not made contact with the table.

    • -

  • The ball is not in the cup but has made contact with the table.

    • -

  • The ball successfully lands in the cup.

    • -

An additional reward component at the final timestep T assesses the chosen ball release time to ensure it falls within a reasonable range. The overall return for an episode is the sum of the rewards at each timestep, the task-specific reward, and the release time reward.

A successful throw in this task is determined by the ball landing in the cup at the episode’s conclusion, showcasing the robot’s ability to accurately predict and execute the complex motion required for this popular party game.

diff --git a/docs/build/html/searchindex.js b/docs/build/html/searchindex.js index 9daa54b..2666042 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, 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 +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, 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, "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, "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], "ha": [8, 10, 21, 22], "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/mujoco.md b/docs/source/envs/fancy/mujoco.md index 018d901..89faeee 100644 --- a/docs/source/envs/fancy/mujoco.md +++ b/docs/source/envs/fancy/mujoco.md @@ -65,13 +65,6 @@ The observation space includes the cosine and sine of the robot's joint angles, Action penalties are implemented in the form of squared torque sums applied across all joints, penalizing excessive force and encouraging efficient motion. The reward function at each timestep t before the final timestep T penalizes the action penalty, while at t=T, a non-Markovian reward based on the ball's position relative to the cup and the action penalty is considered. -Conditions for the task are specified as follows: - -- The ball contacts the ground before touching the table. -- The ball is not in the cup and has not made contact with the table. -- The ball is not in the cup but has made contact with the table. -- The ball successfully lands in the cup. - An additional reward component at the final timestep T assesses the chosen ball release time to ensure it falls within a reasonable range. The overall return for an episode is the sum of the rewards at each timestep, the task-specific reward, and the release time reward. A successful throw in this task is determined by the ball landing in the cup at the episode's conclusion, showcasing the robot's ability to accurately predict and execute the complex motion required for this popular party game.