Ameer Haj Ali 71316fa8d0 wrap models with DistributionalQModel when running DQN (#6258) ...

* wrap models with DistributionalQModel when running DQN

* wrap only for tensorflow models

* Update custom_keras_model.py

2019-11-25 00:11:24 -08:00

..

export

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

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

serving

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

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

__init__.py

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

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

autoregressive_action_dist.py

[rllib] Add autoregressive KL (#5469)

2019-08-19 14:34:50 +08:00

batch_norm_model.py

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

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

cartpole_lstm.py

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

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

centralized_critic_2.py

[tune] Deprecate tune.function (#5601)

2019-08-31 16:00:10 -07:00

centralized_critic.py

Fix typo in examples/centralized_critic.py (#5943)

2019-10-17 08:42:50 -07:00

custom_env.py

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

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

custom_fast_model.py

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

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

custom_keras_model.py

wrap models with DistributionalQModel when running DQN (#6258)

2019-11-25 00:11:24 -08:00

custom_keras_rnn_model.py

Fix TF2 / rllib test (#5846)

2019-10-07 14:25:16 -07:00

custom_loss.py

Custom action distributions (#5164)

2019-08-06 11:13:16 -07:00

custom_metrics_and_callbacks.py

Allow EntropyCoeffSchedule to accept custom schedule (#6158)

2019-11-14 00:45:43 -08:00

custom_tf_policy.py

[rllib] Tracing for eager tensorflow policies with tf.function (#5705)

2019-09-17 01:44:20 -07:00

custom_torch_policy.py

[rllib] Adds eager support with a generic TFEagerPolicy class (#5436)

2019-08-23 14:21:11 +08:00

custom_train_fn.py

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

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

eager_execution.py

[rllib] Adds eager support with a generic TFEagerPolicy class (#5436)

2019-08-23 14:21:11 +08:00

hierarchical_training.py

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

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

multiagent_cartpole.py

[tune] Deprecate tune.function (#5601)

2019-08-31 16:00:10 -07:00

multiagent_custom_policy.py

[tune] Deprecate tune.function (#5601)

2019-08-31 16:00:10 -07:00

multiagent_two_trainers.py

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

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

parametric_action_cartpole.py

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

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

rock_paper_scissors_multiagent.py

Fix linting on master branch (#6174)

2019-11-16 10:02:58 -08:00

rollout_worker_custom_workflow.py

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

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

saving_experiences.py

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

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

twostep_game.py

Qmix on gpu and with non-stacked-obs environment state support (#5751)

2019-10-08 13:18:07 -07:00