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
..
benchmarks Change timeout from milliseconds to seconds in ray.wait. (#3706) 2019-01-08 21:32:08 -08:00
ray [rllib] Support prev_state/prev_action in rollout and fix multiagent (#4565) 2019-04-10 00:01:25 -07:00
asv.conf.json [asv] Pushing to s3 (#2246) 2018-06-20 10:43:44 -07:00
build-wheel-macos.sh Build wheels for macOS with Bazel (#4280) 2019-03-15 10:37:57 -07:00
build-wheel-manylinux1.sh Build wheels for macOS with Bazel (#4280) 2019-03-15 10:37:57 -07:00
README-benchmarks.rst [rllib][asv] Support ASV for RLlib (#2304) 2018-06-28 17:20:09 -07:00
README-building-wheels.md fix wheel building doc (#4360) 2019-03-13 23:11:30 -07:00
setup.py Remove CMake files (#4493) 2019-04-02 22:17:33 -07:00