Asynchronous deep reinforcement learning

An attempt to repdroduce Google Deep Mind's paper "Asynchronous Methods for Deep Reinforcement Learning."

http://arxiv.org/abs/1602.01783

Asynchronous Advantage Actor-Critic (A3C) method for playing "Atari Pong" is implemented with TensorFlow.

Learning result movment after 26 hour is like this.

Any advice or suggestion is strongly welcomed in issues thread.

miyosuda#1

First we need to build multi thread ready version of Arcade Learning Enviroment. I made some modification to it to run it on multi thread enviroment.

$ git clone https://github.com/miyosuda/Arcade-Learning-Environment.git
$ cd Arcade-Learning-Environment
$ cmake -DUSE_SDL=ON -DUSE_RLGLUE=OFF -DBUILD_EXAMPLES=ON .
$ make -j 4

$ pip install .

I recommend to install it on VirtualEnv environment.

To train,

$python a3c.py

To display the result with game play,

$python a3c_disp.py

To enable gpu, change "USE_GPU" flag in "constants.py".

When running with 8 parallel game environemts, speeds of GPU (GTX980Ti) and CPU(Core i7 6700) were like this.

Score plot of local threads of pong in 24h (34.3 million global steps) was like this. (with GTX980Ti)

Scores are not averaged using global network like paper.

This project uses setting written in muupan's wiki [muuupan/async-rl] (https://github.com/muupan/async-rl/wiki)

• @aravindsrinivas for providing information for some of the hyper parameters.