Skip to content

Latest commit

 

History

History
 
 

DeepQNetwork

breakout

video demo

Reproduce (performance of) the following reinforcement learning methods:

Performance & Speed

Claimed performance in the paper can be reproduced, on several games I've tested with.

DQN

On one GTX 1080Ti, the ALE version took ~2 hours of training to reach 21 (maximum) score on Pong, ~10 hours of training to reach 400 score on Breakout. It runs at 100 batches (6.4k trained frames, 400 seen frames, 1.6k game frames) per second on GTX 1080Ti. This is likely the fastest open source TF implementation of DQN.

How to use

With ALE (paper's setting):

Install ALE and gym.

Download an atari rom, e.g.:

wget https://github.com/openai/atari-py/raw/master/atari_py/atari_roms/breakout.bin

Start Training:

./DQN.py --env breakout.bin
# use `--algo` to select other DQN algorithms. See `-h` for more options.

Watch the agent play:

# Download pretrained models or use one you trained:
wget http://models.tensorpack.com/DeepQNetwork/DoubleDQN-Breakout.npz
./DQN.py --env breakout.bin --task play --load DoubleDQN-Breakout.npz

With gym's Atari:

Install gym and atari_py.

./DQN.py --env BreakoutDeterministic-v4

A3C code and models for Atari games in OpenAI Gym are released in examples/A3C-Gym