Lectures

Lecture 1: Introduction. PDF

Lecture 2: Examples of decision problems. PDF

Lecture 3: Bellman's optimality principle. PDF

Lecture 4: Value and Policy iteration. PDF

Lecture 5: Stochastic approximation. PDF

Lecture 6: Convergence of stochastic approximation. PDF

Lecture 7: RL algorithms. PDF

Lecture 8: Bayesian experimental design PDF

Lecture 9: Experimental design with Gaussian Processes PDF

Lecture 10: Partially observable MDPs (POMDPS) PDF

Lecture 11: Exact methods for POMDPS PDF

Lecture 12: Point based value iteration PDF

Lecture 13: Direct policy search

Lecture 13: Representation