Open Rowing0914 opened 5 years ago
This is great! Thanks of the update. I think to make sure these changes don't affect reproducibility, we should bump all the version numbers of affected MuJoCo envs to -V1 in the registration file as well maybe?
Thank you for your prompt response! that's nice!! I'll do that and re-push it!
To test all mujoco envs, please run tests/all_tests.py
(https://github.com/Rowing0914/gym-extensions/blob/mujoco200/tests/all_tests.py)
Thanks! Can you remove the .idea folder that got added. After that I'll run some tests to sanity check that the envs seem ok and an RL agent can still learn on them. Then I'll merge the pull request.
Oh, snap.. deleted it! Thank you for letting me know about that!
I have added the food env, which is a similar concept to AnimalAI(http://animalaiolympics.com/)!! I hope you like it.
I have added extra envs which have been mainly created for NerveNet,https://github.com/WilsonWangTHU/NerveNet, experiments purpose. I modified them to be compatible with MuJoCo ver 2.0, and named them by v1
as we agreed! I hope you like them!
This is the list for newly added envs.
"""
ALL_ENV_LIST = [
WalkersHopperone-v1
WalkersHalfhumanoidone-v1
WalkersHalfcheetahone-v1
WalkersFullcheetahone-v1
WalkersOstrichone-v1
WalkersHoppertwo-v1
WalkersHalfhumanoidtwo-v1
WalkersHalfcheetahtwo-v1
WalkersFullcheetahtwo-v1
WalkersOstrichtwo-v1
WalkersHopperthree-v1
WalkersHalfhumanoidthree-v1
WalkersHalfcheetahthree-v1
WalkersFullcheetahthree-v1
WalkersOstrichthree-v1
WalkersHopperfour-v1
WalkersHalfhumanoidfour-v1
WalkersHalfcheetahfour-v1
WalkersFullcheetahfour-v1
WalkersOstrichfour-v1
WalkersHopperfive-v1
WalkersHalfhumanoidfive-v1
WalkersHalfcheetahfive-v1
WalkersFullcheetahfive-v1
WalkersOstrichfive-v1
CentipedeThree-v1
CentipedeFour-v1
CentipedeFive-v1
CentipedeSix-v1
CentipedeSeven-v1
CentipedeEight-v1
CentipedeTen-v1
CentipedeTwelve-v1
CentipedeFourteen-v1
CentipedeTwenty-v1
CentipedeThirty-v1
CentipedeForty-v1
CentipedeFifty-v1
ReacherZero-v1
ReacherOne-v1
ReacherTwo-v1
ReacherThree-v1
ReacherFour-v1
ReacherFive-v1
ReacherSix-v1
ReacherSeven-v1
SnakeThree-v1
SnakeFour-v1
SnakeFive-v1
SnakeSix-v1
SnakeSeven-v1
SnakeEight-v1
SnakeNine-v1
SnakeTen-v1
SnakeTwenty-v1
SnakeForty-v1
]
"""
and you can test them all from ./tests/nervenet_env_all_test.py
!!
My mujoco environment is 2.0 and python=3.6.2, but it prompts me "You appear to be missing Mujoxo. We expected to find the file here:/home/**/.mujoco/mjpro150"
@zengrui324 sorry, I haven't worked on this project since my last commit... Hope someone can help you... From my memory, maybe you can double check the mujoco path things...
Hi guys,
Thank you for this great repo! Since I had to work on some experiments myself, I modified the repo to the one which is compatible with the latest MuJoCo version 2.0(https://github.com/openai/mujoco-py), which has been released since March in 2019.
So, I hope this enhances more users.