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] Added vanilla policy gradient (#1497)

Browse Source
This commit is contained in:
alvkao58
2018-02-10 13:54:51 -08:00
committed by Richard Liaw
parent 1ab2e63dbd
commit 81a4be8f65
9 changed files with 258 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/source/rllib-dev.rst
+1 -1
View File
@@ -10,7 +10,7 @@ Recipe for an RLlib algorithm
Here are the steps for implementing a new algorithm in RLlib:
1. Define an algorithm-specific `Policy evaluator class <#policy-evaluators-and-optimizers>`__ (the core of the algorithm). Evaluators encapsulate framework-specific components such as the policy and loss functions. For an example, see the `A3C Evaluator implementation <https://github.com/ray-project/ray/blob/master/python/ray/rllib/a3c/a3c_evaluator.py>`__.
1. Define an algorithm-specific `Policy evaluator class <#policy-evaluators-and-optimizers>`__ (the core of the algorithm). Evaluators encapsulate framework-specific components such as the policy and loss functions. For an example, see the `simple policy gradient evaluator example <https://github.com/ray-project/ray/blob/master/python/ray/rllib/pg/pg_evaluator.py>`__.
2. Pick an appropriate `Policy optimizer class <#policy-evaluators-and-optimizers>`__. Optimizers manage the parallel execution of the algorithm. RLlib provides several built-in optimizers for gradient-based algorithms. Advanced algorithms may find it beneficial to implement their own optimizers.