Files
ray/python
Vlad Firoiu 74fd3d7e21 [rllib] Support prev_state/prev_action in rollout and fix multiagent (#4565)
* Cleaner and more correct treatment of agent states in rollout.py

* support lstm_use_prev_action_reward in rollout.py

* Linter.

* appease flake8

* Use _DUMMY_AGENT_ID instead of 0.

* All agents have a policy_agent_mapping.
Reset the mapping cache at the start of each episode.

* Update rollout.py

* Fix rollout.py for single-agent envs.

* Use agent_id, not policy_id.
2019-04-10 00:01:25 -07:00
..
2018-06-20 10:43:44 -07:00
2019-04-02 22:17:33 -07:00