Deep Q Networks (DQN)

• DQN Paper 13
• DQN Nature Paper (little change in algorithm, a bit better performance)

Some Changes and Optimizations

• Prioritized Experience Replay
• Deep Reinforcement Learning with Double Q-learning (Double DQN)
• Asynchronous Methods for Deep Reinforcement Learning (A3C)
• Continuous control with deep reinforcement learning (DDPG)

Deep Reinforcement Learning in 3D environment

• Playing FPS Games with Deep Reinforcement Learning
• Learning to Act by Predicting the Future
• Control of Memory, Active Perception, and Action in Minecraft
• Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning

Experiment Environments

• ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning
• OpenAI Gym