Markov Decision Processes: Dynamic Programming Techniques

Related lectures (32)

Page 2 of 4

Explores accelerating the Value Iteration algorithm using control theory and matrix splitting techniques to achieve faster convergence.

Explores the Asset Selling Problem to maximize long-term reward without a deadline.

Covers the convergence analysis of iterative methods and the conditions for convergence.

Covers the topic of nonlinear equations and the fixed point method.

Explores advanced reinforcement learning topics, including policies, value functions, Bellman recursion, and on-policy TD control.

Covers the introduction to Quantum Chaos, classical chaos, sensitivity to initial conditions, ergodicity, and Lyapunov exponents.

Covers the fixed point method for convergence and linear error reduction.

Explores the Banach Fixed Point Theorem, showing the uniqueness of fixed points in contraction mappings.

Covers fixed point methods and the Picard method for solving nonlinear equations iteratively.

Discusses stopping criteria for fixed point iteration in nonlinear equations and how to manage errors.