Eric Liang 46af992efd [rllib] [experimental] custom RL training pipelines (PG_pl, A2C_pl) (#7213)

2020-02-19 16:07:37 -08:00

..

tests

[rllib] [experimental] custom RL training pipelines (PG_pl, A2C_pl) (#7213)

2020-02-19 16:07:37 -08:00

__init__.py

[rllib] [experimental] custom RL training pipelines (PG_pl, A2C_pl) (#7213)

2020-02-19 16:07:37 -08:00

pg_pipeline.py

[rllib] [experimental] custom RL training pipelines (PG_pl, A2C_pl) (#7213)

2020-02-19 16:07:37 -08:00

pg_tf_policy.py

[rllib] implemented compute_advantages without gae (#6941)

2020-01-31 22:25:45 -08:00

pg_torch_policy.py

[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155)

2020-02-19 12:18:45 -08:00

pg.py

[RLlib] Add torch flag to train.py (#6807)

2020-01-17 18:48:44 -08:00