Eric Liang 9896df7799 [rllib] Guard against PPO value function not training with RNN models (#4037) ...

* better lstm settings

* 1.0

* docs

* warn on truncate

* clarify

* Update ppo_policy_graph.py

* Update ppo_policy_graph.py

* Update ppo_policy_graph.py

2019-02-22 11:18:51 -08:00

..

carla

API cleanups. Remove worker argument. Remove some deprecated arguments. (#4025)

2019-02-15 10:49:16 -08:00

export

[rllib] Export policy model checkpoint (#3637)

2018-12-27 08:43:06 +09:00

serving

[rllib] Rename ServingEnv => ExternalEnv (#3302)

2018-11-12 16:31:27 -08:00

__init__.py

[rllib] Add a simple REST policy server and client example (#2232)

2018-06-20 13:22:39 -07:00

batch_norm_model.py

[rllib] Support batch norm layers (#3369)

2018-11-29 13:33:39 -08:00

cartpole_lstm.py

[rllib] Guard against PPO value function not training with RNN models (#4037)

2019-02-22 11:18:51 -08:00

custom_env.py

[rllib] Add examples page, add hierarchical training example, delete SC2 examples (#3815)

2019-01-29 21:06:09 -08:00

custom_metrics_and_callbacks.py

[rllib] fixes from dogfooding multi-agent (#3456)

2018-12-05 23:31:45 -08:00

custom_train_fn.py

[rllib] Add examples page, add hierarchical training example, delete SC2 examples (#3815)

2019-01-29 21:06:09 -08:00

hierarchical_training.py

[rllib] Add examples page, add hierarchical training example, delete SC2 examples (#3815)

2019-01-29 21:06:09 -08:00

multiagent_cartpole.py

[rllib] Multi-GPU support for Multi-Agent PPO (#3479)

2018-12-08 18:02:33 -08:00

multiagent_two_trainers.py

[rllib] Multi-GPU support for Multi-Agent PPO (#3479)

2018-12-08 18:02:33 -08:00

parametric_action_cartpole.py

[rllib] Documentation for I/O API and multi-agent support / cleanup (#3650)

2019-01-03 15:15:36 +08:00

saving_experiences.py

[rllib] Basic infrastructure for off-policy estimation (IS, WIS) (#3941)

2019-02-13 16:25:05 -08:00

twostep_game.py

[rllib] Q-Mix implementation (Q-Mix, VDN, IQN, and Ape-X variants) (#3548)

2018-12-18 10:40:01 -08:00