Sven Mika 2ccf08ad10 [RLlib] Bug fix: DQN goes into negative epsilon values after reaching explora… (#6971) ...

* Bug fix: DQN goes into negative epsilon values after reaching exploration percentage.

* Add `epsilon_initial_eps` to SAC to pass test_nested_spaces.py.

* Add `exploration_initial_eps` to QMIX default config.

2020-01-31 09:54:12 -08:00

..

a3c

[RLlib] from_config util method for framework agnostic components; start moving RLlib tests into Bazel. (#6865)

2020-01-22 17:02:58 -08:00

ars

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

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

ddpg

[RLlib] Policy-classes cleanup and torch/tf unification. (#6770)

2020-01-17 22:26:28 -08:00

dqn

[RLlib] Bug fix: DQN goes into negative epsilon values after reaching explora… (#6971)

2020-01-31 09:54:12 -08:00

es

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

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

impala

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

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

marwil

[RLlib] Policy-classes cleanup and torch/tf unification. (#6770)

2020-01-17 22:26:28 -08:00

pg

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

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

ppo

[rllib] [experimental] Decentralized Distributed PPO for torch (DD-PPO) (#6918)

2020-01-25 22:36:43 -08:00

qmix

[RLlib] Bug fix: DQN goes into negative epsilon values after reaching explora… (#6971)

2020-01-31 09:54:12 -08:00

sac

[RLlib] Bug fix: DQN goes into negative epsilon values after reaching explora… (#6971)

2020-01-31 09:54:12 -08:00

__init__.py

[rllib] Try moving RLlib to top level dir (#5324)

2019-08-05 23:25:49 -07:00

agent.py

Remove future imports (#6724)

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

mock.py

Remove future imports (#6724)

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

registry.py

Remove future imports (#6724)

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

trainer_template.py

Remove future imports (#6724)

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

trainer.py

[tune] Fix directory naming regression (#6839)

2020-01-27 15:53:40 -08:00