Avnish Narayan 026bf01071 [RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535) 3 年之前
..
tests 026bf01071 [RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535) 3 年之前
__init__.py 4b278c36fc [RLlib] Behavioral Cloning (from MARWIL). (#10619) 4 年之前
bc.py 474f04e322 [RLlib] DDPG/TD3 + A3C/A2C + MARWIL/BC Annotation/Comments/Code Cleanup (#14707) 3 年之前
marwil.py 99a0088233 [RLlib] Unify the way we create local replay buffer for all agents (#19627) 3 年之前
marwil_tf_policy.py 0b308719f8 [RLlib; Docs overhaul] Docstring cleanup: rllib/utils (#19829) 3 年之前
marwil_torch_policy.py cf21c634a3 [RLlib] Fix deprecated warning for torch_ops.py (soft-replaced by torch_utils.py). (#19982) 3 年之前