Kristian HartikainenandEric Liang 13fb9fe3db [rllib] Feature/soft actor critic v2 (#5328) ...

* Add base for Soft Actor-Critic

* Pick changes from old SAC branch

* Update sac.py

* First implementation of sac model

* Remove unnecessary SAC imports

* Prune unnecessary noise and exploration code

* Implement SAC model and use that in SAC policy

* runs but doesn't learn

* clear state

* fix batch size

* Add missing alpha grads and vars

* -200 by 2k timesteps

* doc

* lazy squash

* one file

* ignore tfp

* revert done

2019-08-01 23:37:36 -07:00

..

__init__.py

[rllib] Feature/soft actor critic v2 (#5328)

2019-08-01 23:37:36 -07:00

actors.py

[rllib] Rename PolicyEvaluator => RolloutWorker (#4820)

2019-06-03 06:49:24 +08:00

annotations.py

[rllib] Rename Agent to Trainer (#4556)

2019-04-07 00:36:18 -07:00

compression.py

[rllib] Improve datapath throughput of IMPALA / APPO (#4324)

2019-03-31 12:25:52 -07:00

debug.py

[rllib] Make RLLib handle zero-length observation arrays (#5208)

2019-07-16 22:37:57 -07:00

error.py

[rllib] annotate public vs developer vs private APIs (#3808)

2019-01-23 21:27:26 -08:00

explained_variance.py

[rllib] Remove dependency on TensorFlow (#4764)

2019-05-10 20:36:18 -07:00

filter_manager.py

[rllib] Replace ray.get() with ray_get_and_free() to optimize memory usage (#4586)

2019-04-17 20:30:03 -04:00

filter.py

Enforce quoting style in Travis. (#4589)

2019-04-11 14:24:26 -07:00

memory.py

[rllib] Make RLLib handle zero-length observation arrays (#5208)

2019-07-16 22:37:57 -07:00

policy_client.py

[rllib] annotate public vs developer vs private APIs (#3808)

2019-01-23 21:27:26 -08:00

policy_server.py

Enforce quoting style in Travis. (#4589)

2019-04-11 14:24:26 -07:00

schedules.py

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

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

seed.py

[rllib] Remove dependency on TensorFlow (#4764)

2019-05-10 20:36:18 -07:00

tf_ops.py

[rllib] ModelV2 API (#4926)

2019-07-03 15:59:47 -07:00

tf_run_builder.py

[rllib] fix clip by value issue as TF upgraded (#4697)

2019-05-13 15:39:25 -07:00

timer.py

[rllib] Ape-X implementation and DQN refactor to handle replay in policy optimizer (#1604)

2018-03-04 12:25:25 -08:00

tracking_dict.py

[rllib] Allow Torch policies access to full action input dict in extra_action_out_fn (#4894)

2019-06-01 16:58:49 +08:00

window_stat.py

[rllib] format with yapf (#2427)

2018-07-19 15:30:36 -07:00