/dqn

A pytorch implementation of the deep Q-network (DQN)

Primary LanguagePython

Human-level control through deep reinforcement learning

A pytorch implementation of the deep Q-network (DQN) as introduced in the "Human-level control through deep reinforcement learning" Nature paper. In my implementation, I used the "Space Invaders" Atari game as my main environment.

Table of Contents

  1. Introduction
  2. Requirements
  3. Training and Evaluation Results
  4. Reference