Richard LiawandGitHub dc66a2d7d5 [rllib] A3C Refactoring (#1166) ...

* fixing policy

* Compute Action is singular, fixed weird issue with arrays

* remove vestige

* extraneous ipdb

* Can Drop in Pytorch Model

* lint

* naming

* finish comments

2017-10-29 11:12:17 -07:00

..

__init__.py

[rllib] Rename algorithms (#890)

2017-08-29 16:56:42 -07:00

a3c.py

[rllib] A3C Refactoring (#1166)

2017-10-29 11:12:17 -07:00

common.py

[rllib] A3C Refactoring (#1166)

2017-10-29 11:12:17 -07:00

envs.py

[rllib] Use RLlib preprocessors in DQN (fixes PongDeterministic-v4) (#1124)

2017-10-14 20:16:36 -07:00

policy.py

[rllib] A3C Refactoring (#1166)

2017-10-29 11:12:17 -07:00

runner_thread.py

[rllib] A3C Refactoring (#1166)

2017-10-29 11:12:17 -07:00

runner.py

[rllib] A3C Refactoring (#1166)

2017-10-29 11:12:17 -07:00

shared_model_lstm.py

[rllib] A3C Refactoring (#1166)

2017-10-29 11:12:17 -07:00

shared_model.py

[rllib] A3C Refactoring (#1166)

2017-10-29 11:12:17 -07:00

tfpolicy.py

[rllib] A3C Refactoring (#1166)

2017-10-29 11:12:17 -07:00

torchpolicy.py

[rllib] A3C Refactoring (#1166)

2017-10-29 11:12:17 -07:00