Eric Liang 3c6b94f3f5 [rllib] Enable performance metrics reporting for RLlib pipelines, add A3C (#7299)

2020-02-28 16:44:17 -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] Enable performance metrics reporting for RLlib pipelines, add A3C (#7299)

2020-02-28 16:44:17 -08:00

a2c_pipeline.py

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

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

a2c.py

Remove future imports (#6724)

2020-01-09 00:15:48 -08:00

a3c_pipeline.py

[rllib] Enable performance metrics reporting for RLlib pipelines, add A3C (#7299)

2020-02-28 16:44:17 -08:00

a3c_tf_policy.py

[rllib] implemented compute_advantages without gae (#6941)

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

a3c_torch_policy.py

[RLlib] PPO torch memory leak and unnecessary torch.Tensor creation and gc'ing. (#7238)

2020-02-22 11:02:31 -08:00

a3c.py

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

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