Reinforcement Learning Algorithms

• Proximal Policy Optimization
• This is an experiment that runs a PPO agent on Atari Breakout.
• Generalized advantage estimation
• Deep Q Networks
• This is an experiment that runs a DQN agent on Atari Breakout.
• Model with dueling network
• Prioritized Experience Replay Buffer

This is the implementation for OpenAI game wrapper using multiprocessing .