wassname/DeepRL
1
0
Fork 0
mirror of https://github.com/wassname/DeepRL.git synced 2026-09-09 11:13:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README

Browse Source
This commit is contained in:
Shangtong Zhang
2018-03-13 20:52:51 -06:00
parent 8f75029d69
commit cabc95ff5d
2 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4
View File
@@ -94,6 +94,10 @@ Prediction is sampled after 110K iterations and I only implemented one-step trai
![Loading...](https://raw.githubusercontent.com/ShangtongZhang/DeepRL/master/images/CategoricalDQN.png)
A deterministic test episode is triggered every 10 episodes. 2.5M steps and 14 hours in total.
## A2C & N-Step DQN
![Loading...](https://raw.githubusercontent.com/ShangtongZhang/DeepRL/master/images/A2C-NStepQ.png)
Online training progression of a single run. Entropy regularization is used for A2C, resulting in the variance in the curve.
# Dependency
> Tested in macOS 10.12 and CentO/S 6.8
* Open AI gym
images/A2C-NStepQ.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 223 KiB