rl_theory

We are currently following this book: RL Theory. The slides from the past meetings are available here:

1. 2020/08/27: MDPs
2. 2020/09/08: Value Iteration, Code for Value Iteration
3. 2020/09/23: Policy Iteration
4. 2020/10/06: Q* = TQ* Proof, Concentration Inequalities (Section 1.1, 1.2)
5. 2020/10/20: Sample Complexity