wassname/pytorch-soft-actor-critic
1
0
Fork 0
mirror of https://github.com/wassname/pytorch-soft-actor-critic.git synced 2026-06-27 18:06:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Pranjal Tandon
2018-09-12 08:54:52 +05:30
committed by GitHub
parent 62ae053724
commit 8b5ecb61ea
1 changed files with 4 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -7
View File
@@ -34,13 +34,10 @@ python main.py --env-name Humanoid-v2 --scale_R 20 --tau 1 --value_update 1000
python main.py --env-name Humanoid-v2 --scale_R 20 --deterministic True --tau 1 --value_update 1000
```
### TODO
### Results
------------
My results on Humanoid-v2 environment using SAC and SAC(deterministic, hard update).
This is a plot of average rewards at every 10000 steps interval
- [x] Gaussian Policy
- [x] Reparameterization
- [x] Gaussian Mixture Model
- [x] Use 2 Q-functions
- [x] Evaluate the trained Policy
- [ ] Deterministic Policy (hard target update)
![sacs](https://user-images.githubusercontent.com/18737539/45400165-b2f42980-b668-11e8-8e2b-2b5cdc226204.jpeg)