Skip to content

Hauf3n/DDQN-Atari-PyTorch

Repository files navigation

DQN-Atari-PyTorch

Implementation of (D)-DQN (1) (2) (3) by DeepMind.

Applied to the gym Breakout, Pong and SpaceInvaders environment. *NoFrameskip-v4

Results

games Youtube

Training

Due to computational resource constraints, i trained Breakout and SpaceInvaders for about 11-14 million steps.
The agents would become better given more training.

Training: Breakout
breakout

Training: Pong
breakout

Training: SpaceInvaders
sparse rewards at ~(600-800) return. Often only one/two, fast moving targets left. Hard to optimize! breakout

About

Implementation of (D)-DQN

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published