Deep Reinforcement Learning in Action

Deep Reinforcement Learning in Action
Alexander Zai & Brandon Brown

• Introduction
• Modeling reinforcement learning problems: Markov decision processes
• Predicting the best states and actions: Deep Q-networks
• Learning to pick the best policy: Policy gradient methods
• Tackling more complex problems with actor-critic methods
• Distributional DQN - Getting the full story
• Alternative optimization methods - Evolutionary algorithms
• Curiosity-driven exploration