Pytorch-DDQN implemantaion on Super Mario Brothers

This project implements the paper Human-level control through Deep Reinforcement Learning and Deep Reinforcement Learning with Double Q-learning.

Required

• Human-level control through Deep Reinforcement Learning
• Deep Reinforcement Learning with Double Q-learning
• Going Deeper Into Reinforcement Learning: Understanding Deep-Q-Networks
• Frame Skipping and Pre-Processing for Deep Q-Networks on Atari 2600 Games
• Demystifying Deep Reinforcement Learning

Result

Reference

• transedward/pytorch-dqn
• SSARCandy/pytorch-dqn
• nailo2c/dqn-mario