ray/python/requirements/ml/requirements_rllib.txt

40 lines
963 B
Text
Raw Normal View History

-r requirements_dl.txt
# Environment adapters.
# ---------------------
# Atari
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535) * Fix QMix, SAC, and MADDPA too. * Unpin gym and deprecate pendulum v0 Many tests in rllib depended on pendulum v0, however in gym 0.21, pendulum v0 was deprecated in favor of pendulum v1. This may change reward thresholds, so will have to potentially rerun all of the pendulum v1 benchmarks, or use another environment in favor. The same applies to frozen lake v0 and frozen lake v1 Lastly, all of the RLlib tests and have been moved to python 3.7 * Add gym installation based on python version. Pin python<= 3.6 to gym 0.19 due to install issues with atari roms in gym 0.20 * Reformatting * Fixing tests * Move atari-py install conditional to req.txt * migrate to new ale install method * Fix QMix, SAC, and MADDPA too. * Unpin gym and deprecate pendulum v0 Many tests in rllib depended on pendulum v0, however in gym 0.21, pendulum v0 was deprecated in favor of pendulum v1. This may change reward thresholds, so will have to potentially rerun all of the pendulum v1 benchmarks, or use another environment in favor. The same applies to frozen lake v0 and frozen lake v1 Lastly, all of the RLlib tests and have been moved to python 3.7 * Add gym installation based on python version. Pin python<= 3.6 to gym 0.19 due to install issues with atari roms in gym 0.20 Move atari-py install conditional to req.txt migrate to new ale install method Make parametric_actions_cartpole return float32 actions/obs Adding type conversions if obs/actions don't match space Add utils to make elements match gym space dtypes Co-authored-by: Jun Gong <jungong@anyscale.com> Co-authored-by: sven1977 <svenmika1977@gmail.com>
2021-11-03 08:24:00 -07:00
autorom[accept-rom-license]
gym[atari]==0.21.0; python_version >= '3.7'
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535) * Fix QMix, SAC, and MADDPA too. * Unpin gym and deprecate pendulum v0 Many tests in rllib depended on pendulum v0, however in gym 0.21, pendulum v0 was deprecated in favor of pendulum v1. This may change reward thresholds, so will have to potentially rerun all of the pendulum v1 benchmarks, or use another environment in favor. The same applies to frozen lake v0 and frozen lake v1 Lastly, all of the RLlib tests and have been moved to python 3.7 * Add gym installation based on python version. Pin python<= 3.6 to gym 0.19 due to install issues with atari roms in gym 0.20 * Reformatting * Fixing tests * Move atari-py install conditional to req.txt * migrate to new ale install method * Fix QMix, SAC, and MADDPA too. * Unpin gym and deprecate pendulum v0 Many tests in rllib depended on pendulum v0, however in gym 0.21, pendulum v0 was deprecated in favor of pendulum v1. This may change reward thresholds, so will have to potentially rerun all of the pendulum v1 benchmarks, or use another environment in favor. The same applies to frozen lake v0 and frozen lake v1 Lastly, all of the RLlib tests and have been moved to python 3.7 * Add gym installation based on python version. Pin python<= 3.6 to gym 0.19 due to install issues with atari roms in gym 0.20 Move atari-py install conditional to req.txt migrate to new ale install method Make parametric_actions_cartpole return float32 actions/obs Adding type conversions if obs/actions don't match space Add utils to make elements match gym space dtypes Co-authored-by: Jun Gong <jungong@anyscale.com> Co-authored-by: sven1977 <svenmika1977@gmail.com>
2021-11-03 08:24:00 -07:00
gym[atari]==0.19.0; python_version < '3.7'
# Kaggle envs.
kaggle_environments==1.7.11
# Unity3D testing
#TODO(sven): Add this back to requirements_rllib.txt once mlagents no longer pins torch<1.9.0 version.
#mlagents==0.28.0
mlagents_envs==0.28.0
# For tests on PettingZoo's multi-agent envs.
pettingzoo==1.15.0; python_version >= '3.7'
pymunk==6.0.0
supersuit==3.3.3; python_version >= '3.7'
# For testing in MuJoCo-like envs (in PyBullet).
pybullet==3.2.0
# For tests on RecSim and Kaggle envs.
recsim==0.2.4
tensorflow_estimator==2.6.0
# DeepMind's OpenSpiel
open-spiel==1.0.2
# Other.
# ------
# For MAML on PyTorch.
higher==0.2.1
# For auto-generating an env-rendering Window.
pyglet==1.5.15
imageio-ffmpeg==0.4.5
# Ray Serve example
starlette==0.16.0
# ONNX
onnx==1.9.0
onnxruntime==1.9.0
tf2onnx==1.8.5