Topics covered in this course include:
- Reinforcement Learning methodology and underlying models
- Basic Reinforcement Learning Approaches: Value Iteration, Actor-Critic, Policy iteration
- Exploration / Exploitation Tradeoff: Exploration strategies
- Model-based Reinforcement Learning: Algorithms and model learning techniques
- Reinforcement Learning in Partially Observable systems
- Hierarchical Reinforcement Learning
- Inverse Reinforcement Learning
- Multiagent Reinforcement Learning
- Deep Reinforcement Learning
Exact topics are subject to change and may depend on available time.
