DQN-Pytorch

This repository contains a Pytorch implementation of the paper: Human Level Control Through Deep Reinforcement Learning

REQUIREMENTS

• Pytorch 1.6.0
• Python 3.7
• Open AI Gym

Results

Cartpole-v1 DQN Training Log

• Mean Reward = Average reward over 100 episodes
• Model solved the Cartpole-v1 environment in 631 episodes
• Loss Per Step