1:08:20Abstract Dynamic Programming, Reinforcement Learning, Newton's Method, and Gradient Optimization
A 68-minute video from Dimitri Bertsekas: “Abstract Dynamic Programming, Reinforcement Learning, Newton's Method, and Gradient Optimization”.
7.95K subscribers on YouTube
Shorts, livestreams, trailers and promos are never listed. Unless a curator approved this channel in full, only individually picked videos appear.
1:08:20A 68-minute video from Dimitri Bertsekas: “Abstract Dynamic Programming, Reinforcement Learning, Newton's Method, and Gradient Optimization”.
1:59:20A 119-minute video from Dimitri Bertsekas: “Lecture 1, 2023: Introduction, AlphaZero, Deterministic DP, course overview, ASU”.
1:59:20A 119-minute video from Dimitri Bertsekas: “Lecture 1, 2024, course overview: RL and DP, AlphaZero, discrete and continuous applications”.
2:04:16A 124-minute video from Dimitri Bertsekas: “Lecture 1, 2025, Course overview: RL and DP, AlphaZero, deterministic DP, examples, applications”.
2:11:18A 131-minute video from Dimitri Bertsekas: “Lecture 1, Spring 2022: Introduction, course overview. ASU”.
1:38:20A 98-minute video from Dimitri Bertsekas: “Lecture 10, 2023: On-line training ideas, neural networks and other approximation architectures”.
1:43:23A 103-minute video from Dimitri Bertsekas: “Lecture 10, 2024; GPT, HMM, and Markov chains: Rollout variants for most likely sequence generation”.
1:32:12A 92-minute video from Dimitri Bertsekas: “Lecture 10, 2025; Aggregation Methods for Off-Line Training, Applications to POMDP and Cybersecurity”.
2:27:21A 147-minute video from Dimitri Bertsekas: “Lecture 10, Spring 2022: Approximate policy iteration, variations, and Q-learning. Spring 2022, ASU”.
1:44:36A 105-minute video from Dimitri Bertsekas: “Lecture 11, 2023: Review of off-line training, approximate VI and PI, aggregation, course overview”.
1:38:04A 98-minute video from Dimitri Bertsekas: “Lecture 11, 2024: On-line training, neural networks, and other approximation architectures”.
1:15:27A 75-minute video from Dimitri Bertsekas: “Lecture 11, 2025; Adversarial Problems, Minimax Rollout, Use of MPC Methods, Computer Chess”.
1:41:44A 102-minute video from Dimitri Bertsekas: “Lecture 11, Spring 2022: Approximate linear programming; policy gradients and random search. ASU”.
1:29:29A 89-minute video from Dimitri Bertsekas: “Lecture 12 2024; Off-line training with neural nets for approximate VI and PI. Aggregation”.
2:11:08A 131-minute video from Dimitri Bertsekas: “Lecture 12, 2021: Aggregation methods and approximation in value space. ASU.”.
1:25:33A 86-minute video from Dimitri Bertsekas: “Lecture 12, 2025; Training of cost functions, approximation in policy space, policy gradient methods”.
1:33:28A 93-minute video from Dimitri Bertsekas: “Lecture 12, Spring 2022: Aggregation methods for off-line training. Spring 2022, ASU”.
1:21:08A 81-minute video from Dimitri Bertsekas: “Lecture 13 2024: Approximate LP. Approximation in policy space, policy gradient methods. Epilogue”.
2:37:01A 157-minute video from Dimitri Bertsekas: “Lecture 13, 2021: An overview of the entire course. Discussion. ASU.”.
2:35:03A 155-minute video from Dimitri Bertsekas: “Lecture 13, Spring 2022: An overview of the entire course, ASU”.
2:04:42A 125-minute video from Dimitri Bertsekas: “Lecture 2, 2023: Stochastic DP for finite and Infinite horizon, Approximation in value space. ASU”.
2:10:00A 130-minute video from Dimitri Bertsekas: “Lecture 2, 2024, Stochastic finite and infinite horizon DP, approximation in value and policy space”.
2:06:50A 127-minute video from Dimitri Bertsekas: “Lecture 2, 2025, Stochastic finite and infinite horizon DP, approximation in value and policy space”.
2:01:35A 122-minute video from Dimitri Bertsekas: “Lecture 2, Spring 2022: Stochastic DP, finite and infinite horizon. ASU”.
1:54:24A 114-minute video from Dimitri Bertsekas: “Lecture 3, 2023: Approximation in value space as Newton step. DP problem formulation in practice.”.
1:42:27A 102-minute video from Dimitri Bertsekas: “Lecture 3, 2024, LQ Problems, Approximation in Value Space, VI, and PI, Newton's Method, Examples”.
1:25:24A 85-minute video from Dimitri Bertsekas: “Lecture 3, 2025, LQ Problems, Approximation in Value Space, VI, and PI, Newton's Method, Examples”.
2:01:37A 122-minute video from Dimitri Bertsekas: “Lecture 3, Spring 2022: Approximation in value space as Newton's method. ASU”.
1:25:40A 86-minute video from Dimitri Bertsekas: “Lecture 4, 2023: Systems with unknown parameters and adaptive control. Model predictive control.”.
1:50:32A 111-minute video from Dimitri Bertsekas: “Lecture 4, 2025, POMDP, Systems with Changing Parameters, Adaptive Control, Model Predictive Control”.
1:49:06A 109-minute video from Dimitri Bertsekas: “Lecture 4, Spring 2022: Adaptive Control. Value and Policy Approximations in DP/RL. ASU”.
1:40:53A 101-minute video from Dimitri Bertsekas: “Lecture 5, 2023: Rollout algorithms for deterministic DP problems, and variations”.
1:30:28A 90-minute video from Dimitri Bertsekas: “Lecture 5, 2024, Deterministic Rollout, cost improvement, sequential improvement, multiagent rollout”.
1:58:08A 118-minute video from Dimitri Bertsekas: “Lecture 5, 2025, Deterministic Rollout and Animations”.
1:47:16A 107-minute video from Dimitri Bertsekas: “Lecture 5, Spring 2022: Rollout for Deterministic and Stochastic DP; Monte Carlo Tree Search. ASU”.
1:50:42A 111-minute video from Dimitri Bertsekas: “Lecture 6 2023: Deterministic multistep lookahead, constrained rollout, discrete/integer programming”.