Video links

The lecture recordings of the courses in the course links, arranged by chapter. The reading plan gives the matching slides and readings. Where it identifies no individual video, the entry below links to the course playlist and is marked (playlist); the lecture number locates the recording there. Harvard CS2824, Cornell CS6789, and Szepesvári’s CMPUT 653 are used through their slides and notes, with no recordings linked, so they appear only in the reading plan.

Video or playlist	Link	Notes
DeepMind x UCL Reinforcement Learning Lecture Series, 2021	Playlist	Thirteen lectures; the numbers below are lecture numbers. YouTube labels the playlist as a deep-learning series.
UCL, 2015 — David Silver	Playlist	Ten lectures; the numbers below are lecture numbers.
UC Berkeley CS285, Fall 2023	Playlist	Each lecture is split into several videos; the links below open the first part, and the numbers are lecture numbers.
UC Berkeley CS285, Spring 2026	Playlist	Lectures 8 and 14, on Q-learning in practice and on RL with sequences and language models (chapters 18 and 28).
Stanford CS234, Spring 2024	Playlist	The numbers below are lecture numbers; only lecture 1 is linked individually.
Stanford CS224R, Spring 2025	Playlist	The reading plan links the 2026 slides; the 2025 recordings cover the same lectures under the same numbers.
Pieter Abbeel, Foundations of Deep RL, 2021	Playlist	Six lectures; the numbers below are lecture numbers.
UC Berkeley CS287, Fall 2019	Course page	The course page links the slides and videos; the numbers below are lecture numbers.
CMU 16-745, 2025	Playlist	The numbers below are lecture numbers.
Multi-Agent Reinforcement Learning lectures	Playlist	Lectures on the book of Albrecht, Christianos, and Schäfer, with slides (chapter 27).
Nathan Lambert, RLHF course	Course	Lectures 3–5 on policy-gradient algorithms for language models and reasoning (chapter 28).
Princeton ECE524, Spring 2024	Playlist	Lectures on the foundations of RL theory (chapter 30).
University of Alberta, Reinforcement Learning Specialization	Coursera	Short videos that follow Sutton and Barto through Part I (chapters 1–3, 5–7, 10–11, and 13); not listed by chapter below.

By chapter

Chapter	DeepMind x UCL 2021 lectures	Silver 2015 lectures	CS285 lectures	Other recordings
1. Markov Decision Processes	1: Introduction to reinforcement learning · 3: MDPs and dynamic programming, first half	1: Introduction · 2: Markov decision processes	4: Introduction to reinforcement learning	CS234 1: Introduction
2. Dynamic Programming	3: MDPs and dynamic programming · 4: Theoretical fundamentals of dynamic programming	3: Planning by dynamic programming	—	CS234 2: Tabular MDP planning (playlist)
3. Multi-Armed Bandits	2: Exploration and control	9: Exploration and exploitation	—	CS234 11: Fast reinforcement learning, bandits (playlist) · CS234 12: Bayesian bandits (playlist)
4. Contextual, Bayesian, and Adversarial Bandits	—	—	—	CS234 12: Bayesian bandits (playlist) · CS234 13: Fast reinforcement learning III (playlist)
5. Monte Carlo Methods	5: Model-free prediction	4: Model-free prediction	—	CS234 3: Model-free policy evaluation (playlist)
6. Temporal-Difference Learning	5: Model-free prediction	4: Model-free prediction	—	—
7. Model-Free Control	6: Model-free control	5: Model-free control	—	CS234 4, first half: Model-free control (playlist)
8. Multi-Step Bootstrapping and Eligibility Traces	11: Multi-step and off-policy	4, second part: TD(λ)	—	—
9. Off-Policy Learning	11: Multi-step and off-policy	—	—	CS234 10: Offline RL and policy evaluation (playlist)
10. Planning and Learning with Tabular Models	8: Model-based reinforcement learning (playlist)	8: Integrating learning and planning	—	CS234 14: Monte Carlo tree search (playlist)
11. Value Function Approximation	7: Function approximation	6: Value function approximation	7: Value function methods	CS287 4: MDPs and function approximation
12. The Deadly Triad and Gradient-TD Methods	10: Approximate dynamic programming (playlist)	—	—	—
13. Policy Gradient and Actor-Critic Methods	9: Policy gradients and actor-critics	7: Policy gradient methods	5: Policy gradients · 6: Actor-critic algorithms	Abbeel 3: Policy gradients and advantage estimation · CS234 5: Policy search (playlist)
14. Partially Observable Environments	—	—	—	CS287 15: POMDPs
15. Optimal Control and Trajectory Optimization	—	—	10: Optimal control and planning	CS287 5: LQR, iterative LQR, and DDP · CS287 8: Optimization for optimal control · 16-745 8: LQR three ways · 16-745 10: Convex MPC · 16-745 12: Differential dynamic programming · 16-745 13: Direct trajectory optimization
16. Deep Q-Learning	12: Deep reinforcement learning, part 1 · 13: Deep reinforcement learning, part 2 (playlist)	—	8: Deep RL with Q-functions (playlist)	Abbeel 2: Deep Q-learning
17. Distributional Reinforcement Learning	—	—	—	—
18. Data-Efficient and Scalable Value-Based Agents	—	—	Spring 2026, 8: Q-learning in practice (playlist)	—
19. Deep Actor-Critic and Distributed RL	—	—	6: Actor-critic algorithms	—
20. Trust Regions and Proximal Policy Optimization	—	—	9: Advanced policy gradients	Abbeel 4: TRPO and PPO · CS234 6: Policy gradient II (playlist) · CS234 7: Policy gradients and imitation learning (playlist)
21. Continuous Control and Maximum-Entropy RL	—	—	18: Variational inference · 19: Control as inference (playlist)	Abbeel 1: Exact methods and maximum-entropy RL · Abbeel 5: DDPG and SAC (playlist) · CS224R 5: Off-policy actor-critic (playlist)
22. Exploration in Deep RL	—	—	13: Exploration (playlist) · 14: Exploration, continued (playlist)	CS234 13: Fast reinforcement learning III (playlist)
23. Model-Based RL and World Models	8: Model-based reinforcement learning (playlist)	—	11: Model-based RL (playlist) · 12: Model-based policy learning (playlist)	Abbeel 6: Model-based RL (playlist)
24. Planning with Learned Models	—	10: Classic games	—	CS234 14: Monte Carlo tree search (playlist)
25. Imitation Learning and Inverse RL	—	—	2: Supervised learning of behaviors · 20: Inverse reinforcement learning	CS234 7: Policy gradients and imitation learning (playlist) · CS234 8: Imitation learning and RLHF (playlist) · CS224R 2: Imitation learning (playlist) · CS224R 8: Reward learning (playlist) · CS287 17: Imitation learning
26. Offline Reinforcement Learning	—	—	15: Offline reinforcement learning · 16: Offline reinforcement learning, continued (playlist)	CS234 10: Offline RL (playlist) · CS224R 7: Offline RL (playlist)
27. Multi-Agent RL and Self-Play	—	10: Classic games	—	MARL book lectures
28. Reinforcement Learning for Language Models and Reasoning	—	—	Spring 2026, 14: RL with sequences and language models (playlist)	Lambert 3: Understanding policy-gradient algorithms for RL on LLMs · Lambert 4: Implementing policy-gradient algorithms · Lambert 5: The rise of reasoning models · CS224R 9: RLHF (playlist) · CS224R 10: RL for language-model reasoning (playlist)
29. Generalist Agents, Meta-RL, and Open-Endedness	—	—	22: Meta-learning and transfer (playlist)	CS224R 12: Multi-task and goal-conditioned RL (playlist) · CS224R 13: Meta-RL (playlist) · CS224R 17: RL on real robots with pretrained foundation models (playlist)
30. The Theory of Reinforcement Learning	—	—	17: Reinforcement learning theory basics (playlist)	Princeton ECE524 lectures
31. Reinforcement Learning in the Real World	—	—	23: Challenges and open problems (playlist)	CS287 22: Sim-to-real and domain randomization (Josh Tobin) · CS224R 15: Hierarchy (playlist) · CS224R 16: Sim-to-real and robot learning (playlist)