Onur
|
38f301dffb
|
remove reward_function attribute from Beerpong env
|
2022-07-05 13:12:47 +02:00 |
|
Onur
|
69de4286b3
|
beerpong only one file
|
2022-07-05 10:12:01 +02:00 |
|
Onur
|
4dc33b0e97
|
slim down beerpong constructor further. Not sure, if we should merge the reward into the environment class.
|
2022-07-04 19:14:31 +02:00 |
|
Onur
|
d80df03145
|
minor changes at beerpong during call with Fabian
|
2022-07-04 11:29:51 +02:00 |
|
Onur
|
2161cfd3a6
|
Fix bugs to create mp environments. Still conflicts with mp_pytorch_lib
|
2022-07-01 11:42:42 +02:00 |
|
Onur
|
d4e3b957a9
|
finish up beerpong, walker2d and ant needs more extensions, fix import bugs.
|
2022-07-01 09:54:42 +02:00 |
|
Onur
|
4437ab9577
|
change accessing body position in beerpong.py
|
2022-06-30 18:17:02 +02:00 |
|
Onur
|
a7051cd8b7
|
mainly tidied up beerpong.py and beerpong_reward_staged.py
|
2022-06-30 17:55:00 +02:00 |
|
Fabian
|
fea2ae7d11
|
current state
|
2022-06-30 17:33:05 +02:00 |
|
Onur
|
60bdeef687
|
Merge remote-tracking branch 'origin/clean_api' into clean_api
# Conflicts:
# alr_envs/alr/mujoco/reacher/__init__.py
|
2022-06-30 14:56:06 +02:00 |
|
Onur
|
f31d85451f
|
adjust env registries in __init__
|
2022-06-30 14:55:34 +02:00 |
|
Fabian
|
c3a8352c63
|
call on superclass for obs wrapper
|
2022-06-30 14:20:52 +02:00 |
|
Fabian
|
3273f455c5
|
wrappers updated
|
2022-06-30 14:08:54 +02:00 |
|
Fabian
|
fb4b857fb5
|
Merge remote-tracking branch 'origin/clean_api' into clean_api
|
2022-06-29 16:30:51 +02:00 |
|
Fabian
|
b200cf4b69
|
sequencing and replanning
|
2022-06-29 16:30:36 +02:00 |
|
Fabian
|
9b48fc9d48
|
todos
|
2022-06-29 12:25:40 +02:00 |
|
Onur
|
a042f9f671
|
fix dict copy issue
|
2022-06-29 11:55:40 +02:00 |
|
Onur
|
6e06e11cfa
|
added new mp wrappers to all environments
|
2022-06-29 10:39:28 +02:00 |
|
Fabian
|
02b8a65bab
|
restructuring
|
2022-06-29 09:37:18 +02:00 |
|
Onur
|
8fe6a83271
|
started cleaning up init. DMP envs are still not transferred. Wrappers for various environments still missing
|
2022-06-28 20:33:19 +02:00 |
|
Fabian Otto
|
9ad6fbe712
|
first clean up and some non working ideas sketched
|
2022-06-28 16:05:09 +02:00 |
|
Onur
|
7bd9848c31
|
after deadline
|
2022-06-21 17:15:01 +02:00 |
|
Onur
|
c47845c0dd
|
prepare HJ for PPO
|
2022-06-05 15:11:07 +02:00 |
|
Onur
|
719b40c4e4
|
update bp step based env
|
2022-06-04 17:43:35 +02:00 |
|
Onur
|
8b8be4b582
|
smaller ctxt range hopper jump + step-based rew for bp
|
2022-06-04 15:27:20 +02:00 |
|
Onur
|
24604e60be
|
bp step based -> release time for PPO
|
2022-06-02 09:05:38 +02:00 |
|
Onur
|
59b15e82ea
|
bp 2fs seems to work
|
2022-05-31 19:41:08 +02:00 |
|
Onur
|
2ea7f6a2ed
|
bp_frameskip_dev
|
2022-05-29 13:57:33 +02:00 |
|
Onur
|
9b4a0f89b6
|
bp frameskip sanity check
|
2022-05-29 13:32:45 +02:00 |
|
Onur
|
3cc1cd1456
|
bp frameskip version
|
2022-05-29 12:15:04 +02:00 |
|
Onur
|
863ef77e5e
|
safety
|
2022-05-29 11:59:02 +02:00 |
|
Onur
|
f1a96c055b
|
safety
|
2022-05-29 11:58:01 +02:00 |
|
Onur
|
647f086a8d
|
remove unnecessary code lines
|
2022-05-17 10:31:47 +02:00 |
|
Onur
|
2cc1ab759c
|
commit last version of
|
2022-05-05 18:50:20 +02:00 |
|
Fabian
|
a26b9f463b
|
Merge branch 'master' into dev_new_mp_api
Conflicts:
alr_envs/alr/__init__.py
|
2022-05-05 16:57:40 +02:00 |
|
Fabian
|
bd4632af84
|
hole_reacher update
|
2022-05-05 16:54:39 +02:00 |
|
Fabian
|
ad30e732c8
|
reacher adjustments
|
2022-05-05 16:53:56 +02:00 |
|
Fabian
|
1881c14a48
|
reacher adjustments
|
2022-05-05 16:48:59 +02:00 |
|
Onur
|
640f3b2d90
|
fix action space bugs for bp
|
2022-05-03 21:34:39 +02:00 |
|
Onur
|
2fbde9fbb1
|
working bp version
|
2022-05-03 19:51:54 +02:00 |
|
Onur
|
f33996c27a
|
include callback in step
|
2022-05-02 15:06:21 +02:00 |
|
Onur
|
137eb726eb
|
mp_pytorch now running with zero start/goal promp, but delay is not working
|
2022-04-29 18:46:09 +02:00 |
|
Onur
|
cd33e82d3c
|
start integrating mp_pytorch lib
|
2022-04-28 09:05:28 +02:00 |
|
Onur
|
7f64c975cd
|
shorter number of release steps for beerpong
|
2022-04-27 16:15:17 +02:00 |
|
Onur
|
a9460f15fd
|
fix small reacher issues for optimal control
|
2022-04-22 15:36:19 +02:00 |
|
Onur
|
c0502cf1d4
|
corrected reward for hopperjumprndminit + ALRReacher for iLQR
|
2022-04-21 08:44:13 +02:00 |
|
Onur
|
77927e9157
|
improve randomization hopperjump-v2
|
2022-04-20 17:51:43 +02:00 |
|
Onur
|
855ddcee4b
|
hopperjump-v2 -> init pos randomized
|
2022-04-20 14:50:02 +02:00 |
|
Onur
|
1c9019ab08
|
added non-contextual envs
|
2022-04-20 10:50:41 +02:00 |
|
Onur
|
092525889b
|
Added environments from Paul + Marc
|
2022-04-13 17:28:25 +02:00 |
|