8000 PARL/examples/DQN at lkj_lib · NetHole/PARL · GitHub
[go: up one dir, main page]

Skip to content

Latest commit

 

History

History
 
 

DQN

README.md

Reproduce DQN with PARL

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

Atari games introduction

Please see here to know more about Atari games.

Benchmark result

Mean episode rewards for 10 million training steps.

pong

Performance of DQN on various environments

result

How to use

Dependencies:

Start Training:

# To train a model for Pong game
python train.py --rom ./rom_files/pong.bin

To train more games, you can install more rom files from here.

0