Dimitri Bertsekas

Reinforcement Learning, Model Predictive Control, and the Newton Step for Solving Bellman's Equation

Dimitri Bertsekas

Lecture 12, 2025; Training of cost functions, approximation in policy space, policy gradient methods

Dimitri Bertsekas

Abstract Dynamic Programming, Reinforcement Learning, Newton's Method, and Gradient Optimization

Dimitri Bertsekas

Lecture 11, 2025; Adversarial Problems, Minimax Rollout, Use of MPC Methods, Computer Chess

Dimitri Bertsekas

Lecture 10, 2025; Aggregation Methods for Off-Line Training, Applications to POMDP and Cybersecurity

Dimitri Bertsekas

Lecture 9, 2025; Rollout and Its Variants for Stochastic and Adaptive Control, Application to Wordle

Dimitri Bertsekas

Lecture 8, 2025; GPT, HMM, and Markov chains Rollout variants for most likely sequence generation

Dimitri Bertsekas

New Directions in RL TD(lambda), aggregation, seminorm projections, free-form sampling (from 2014)

Dimitri Bertsekas

Lecture 7, 2025, Case studies Multi-robot warehouse, data association

Dimitri Bertsekas

Lecture 6, 2025, Multistep Approximation in Value Space, Constrained Rollout, Multiagent Rollout

Dimitri Bertsekas

Lecture 5, 2025, Deterministic Rollout and Animations

Dimitri Bertsekas

Lecture 4, 2025, POMDP, Systems with Changing Parameters, Adaptive Control, Model Predictive Control

Dimitri Bertsekas

Lecture 3, 2025, LQ Problems, Approximation in Value Space, VI, and PI, Newton's Method, Examples

Dimitri Bertsekas

Computer chess with model predictive control and reinforcement learning

Dimitri Bertsekas

Lecture 2, 2025, Stochastic finite and infinite horizon DP, approximation in value and policy space

Dimitri Bertsekas

Lecture 1, 2025, Course overview RL and DP, AlphaZero, deterministic DP, examples, applications

Dimitri Bertsekas

Plenary lecture at IFAC Nonlinear MPC, 2024; Model Predictive Control and Reinforcement Learning

Dimitri Bertsekas

Lecture 1, 2024, course overview RL and DP, AlphaZero, discrete and continuous applications

Dimitri Bertsekas

Lecture 13 2024 Approximate LP. Approximation in policy space, policy gradient methods. Epilogue

Dimitri Bertsekas

Lecture 12 2024; Off-line training with neural nets for approximate VI and PI. Aggregation

Dimitri Bertsekas

Lecture 11, 2024 On-line training, neural networks, and other approximation architectures

Dimitri Bertsekas

Lecture 10, 2024; GPT, HMM, and Markov chains Rollout variants for most likely sequence generation

Dimitri Bertsekas

Lecture 9, 2024, Bayesian optimization and adaptive control with a POMDP approach. Wordle case study

Dimitri Bertsekas

Acceptance remarks by Dimitri Bertsekas for 2014 Khachiyan Prize of the INFORMS Optimization Society

Dimitri Bertsekas

Lecture 8, 2024, Rollout for stochastic DP. Value space approx for infinite state and control spaces

Dimitri Bertsekas

Lecture 7, 2024, Case studies Multi-robot warehouse, multiagent routing, data association

Dimitri Bertsekas

Lecture 6, 2024, Multistep Approximation in Value Space, Constrained Rollout, Multiagent Rollout

Dimitri Bertsekas

Lecture 5, 2024, Deterministic Rollout, cost improvement, sequential improvement, multiagent rollout

Dimitri Bertsekas

Lecture 4, 2024, POMDP, Systems with Changing Parameters, Adaptive Control, Model Predictive Control

Dimitri Bertsekas

Polyhedral Approximation Algorithms for Convex Optimization, NIPS 2008

Dimitri Bertsekas