Program

Confirmed topics:

• MDPs and Dynamic Programming
• Temporal Difference Methods
• Policy Gradient
• Contextual Bandits
• Stochastic Bandits
• Exploration in RL (optimism)
• Concentration Inequalities
• Monte-Carlo Tree Search

Tentative topics to cover might include:

Representation Learning and RL, Hierarchical RL, Neuroscience and more.

More to be announced soon!