wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-09 12:20:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Merge DDPG and DDPG2 implementations (#2202)

Browse Source 
* removed ddpg2

* removed ddpg2 from codebase

* added tests used in ddpg vs ddpg2 comparison

* added notes about training timesteps to yaml files

* removed ddpg2 yaml files

* removed unnecessary configs from yaml files

* removed unnecessary configs from yaml files

* moved pendulum, mountaincarcontinuous, and halfcheetah tests to tuned_examples

* moved pendulum, mountaincarcontinuous, and halfcheetah tests to tuned_examples

* added more configuration details to yaml files

* removed random starts from halfcheetah
This commit is contained in:
andrewztan
2018-06-09 16:46:23 -07:00
committed by Richard Liaw
parent 3b5e700fd7
commit 1475600c81
14 changed files with 185 additions and 520 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/source/rllib.rst
+1 -1
View File
@@ -15,7 +15,7 @@ RLlib's policy optimizers serve as the basis for RLlib's reference algorithms, w
- Deep Q Networks (`DQN <https://github.com/ray-project/ray/tree/master/python/ray/rllib/dqn>`__).
- Deep Deterministic Policy Gradients (`DDPG <https://github.com/ray-project/ray/tree/master/python/ray/rllib/ddpg>`__, `DDPG2 <https://github.com/ray-project/ray/tree/master/python/ray/rllib/ddpg2>`__).
- Deep Deterministic Policy Gradients (`DDPG <https://github.com/ray-project/ray/tree/master/python/ray/rllib/ddpg>`__).
- Ape-X Distributed Prioritized Experience Replay, including both `DQN <https://github.com/ray-project/ray/blob/master/python/ray/rllib/dqn/apex.py>`__ and `DDPG <https://github.com/ray-project/ray/blob/master/python/ray/rllib/ddpg/apex.py>`__ variants.