8000 PARL/examples/OAC at develop · woshiwangbuer/PARL · GitHub
[go: up one dir, main page]

Skip to content

Latest commit

 

History

History
 
 

OAC

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 

README.md

Reproduce OAC with PARL

Based on PARL, the OAC algorithm of deep reinforcement learning has been reproduced, reaching the same level of indicators as the paper in Mujoco benchmarks.

Paper: OAC in Better Exploration with Optimistic Actor-Critic

Mujoco games introduction

Please see here to know more about Mujoco games.

Benchmark result

OAC_results

How to use

Dependencies:

Start Training:

# To train an agent for Humanoid-v1 game
python train.py

# To train for other game
python train.py --env [ENV_NAME]
0