A2C

Reproduce A2C with PARL

Based on PARL, the A2C algorithm of deep reinforcement learning has been reproduced, reaching the same level of indicators as the paper in Atari benchmarks.

Atari game introduction

Please see here to know more about Atari games.

Benchmark result

Performance of A2C on some envrionments in training process after 10 million sample steps.

How to use

Dependencies

• paddlepaddle>=2.0.0
• parl>=1.4.3
• gym==0.12.1
• atari-py==0.1.7

Distributed Training

At first, we can start a local cluster with 5 CPUs:

xparl start --port 8010 --cpu_num 5

Note that if you have started a master before, you don't have to run the above command. For more information about the cluster, please refer to our documentation

Then we can start the distributed training by running:

python train.py

Reference

• Parl
• Ray
• OpenAI Baselines: ACKTR & A2C