ray/rllib/policy
2022-07-15 09:17:06 +02:00
..
tests [RLlib] Fix docstring and add unit tests for rnn sequencing. (#26197) 2022-07-06 14:32:57 +02:00
__init__.py [RLlib] JAXPolicy prep. PR #1. (#13077) 2020-12-26 20:14:18 -05:00
dynamic_tf_policy.py [RLlib] Include SampleBatch.T column in all collected batches. (#25926) 2022-06-21 13:20:22 +02:00
dynamic_tf_policy_v2.py [RLlib] Migrating DDPG to PolicyV2. (#26054) 2022-06-28 15:52:56 +02:00
eager_tf_policy.py [RLlib] Save serialized PolicySpec. Extract num_gpus related logics into a util function. (#25954) 2022-06-30 11:38:21 +02:00
eager_tf_policy_v2.py [RLlib] Save serialized PolicySpec. Extract num_gpus related logics into a util function. (#25954) 2022-06-30 11:38:21 +02:00
policy.py [RLlib] Fix a bunch of issues related to connectors. (#26510) 2022-07-13 18:55:20 +02:00
policy_map.py [RLlib] Checkpoint and restore connectors. (#26253) 2022-07-09 01:06:24 -07:00
policy_template.py [RLlib] Trainer to Algorithm renaming. (#25539) 2022-06-11 15:10:39 +02:00
rnn_sequencing.py [RLlib] Fix docstring and add unit tests for rnn sequencing. (#26197) 2022-07-06 14:32:57 +02:00
sample_batch.py [RLlib] Fix sample batch concat samples. (#25572) 2022-06-14 12:47:29 +02:00
tf_mixins.py [RLlib] Make DQN update_target use only trainable variables. (#25226) 2022-07-15 09:17:06 +02:00
tf_policy.py [RLlib] Save serialized PolicySpec. Extract num_gpus related logics into a util function. (#25954) 2022-06-30 11:38:21 +02:00
tf_policy_template.py [RLlib] Trainer to Algorithm renaming. (#25539) 2022-06-11 15:10:39 +02:00
torch_mixins.py [RLlib] More Trainer -> Algorithm renaming cleanups. (#25869) 2022-06-20 15:54:00 +02:00
torch_policy.py [RLlib] Save serialized PolicySpec. Extract num_gpus related logics into a util function. (#25954) 2022-06-30 11:38:21 +02:00
torch_policy_template.py [RLlib] Trainer to Algorithm renaming. (#25539) 2022-06-11 15:10:39 +02:00
torch_policy_v2.py [RLlib] Save serialized PolicySpec. Extract num_gpus related logics into a util function. (#25954) 2022-06-30 11:38:21 +02:00
view_requirement.py Clean up docstyle in python modules and add LINT rule (#25272) 2022-06-01 11:27:54 -07:00