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
2017-07-30 13:36:15 -06:00
parent bbfcbf76f4
commit 473304d9a7
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -2
View File
@@ -25,14 +25,16 @@ Xeon E5-2620 v3 and Titan X. For Breakout, test is triggered every 1000 episodes
In total, 16M frames cost about 4 days and 10 hours. For Pong, test is triggered
every 10 episodes with no repetition. In total, 4M frames cost about 18 hours.
## A3C
## A3C, etc.
![Loading...](https://raw.githubusercontent.com/ShangtongZhang/DeepRL/master/images/A3C-Pong.png)
![Loading...](https://raw.githubusercontent.com/ShangtongZhang/DeepRL/master/images/Async-Pong.png)
The network I used here is a smaller network with only 42 * 42 input, alougth the network for DQN can also work here,
it's quite slow.
Training took about 2 hours (16 processes) in a server with two Xeon E5-2620 v3.
Training of A3C took about 2 hours (16 processes) in a server with two Xeon E5-2620 v3. While other async methods took about 1 day.
Those value based async methods do work but I don't know how to make them stable.
This is the test curve. Test is triggered in a separate deterministic test process every 50K frames.
# Dependency
images/Async-Pong.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 552 KiB