wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-12 12:20:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* 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
This commit is contained in:
Kristian Hartikainen
2019-08-01 23:37:36 -07:00
committed by Eric Liang
parent 3ae54a2b20
commit 13fb9fe3db
21 changed files with 827 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/source/rllib-training.rst
+1 -1
View File
@@ -37,7 +37,7 @@ The ``rllib train`` command (same as the ``train.py`` script in the repo) has a
The most important options are for choosing the environment
with ``--env`` (any OpenAI gym environment including ones registered by the user
can be used) and for choosing the algorithm with ``--run``
(available options are ``PPO``, ``PG``, ``A2C``, ``A3C``, ``IMPALA``, ``ES``, ``DDPG``, ``DQN``, ``MARWIL``, ``APEX``, and ``APEX_DDPG``).
(available options are ``SAC``, ``PPO``, ``PG``, ``A2C``, ``A3C``, ``IMPALA``, ``ES``, ``DDPG``, ``DQN``, ``MARWIL``, ``APEX``, and ``APEX_DDPG``).
Evaluating Trained Policies
~~~~~~~~~~~~~~~~~~~~~~~~~~~