IIT Madras · Computer Science

Reinforcement Learning

Prof. Balaraman Ravindran · 2024 · 60 free video lectures

Reinforcement learning is a paradigm that aims to model the trial-and-error learning process that is needed in many problem situations where explicit instructive signals are not available. It has roots in operations research, behavioral psychology and AI. The goal of the course is to introduce the…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Introduction to RL
  2. RL Framework and Applications
  3. Introduction to Immediate RL
  4. Bandit Optimalities
  5. Value Function Based Methods
  6. UCB 1
  7. Concentration Bounds
  8. UCB 1 Theorem
  9. PAC Bounds
  10. Median Elimination
  11. Thompson Sampling
  12. Policy Search
  13. REINFORCE
  14. Contextual Bandits
  15. Full RL Introduction
  16. Returns, Value Functions and MDPs
  17. MDP Modelling
  18. Bellman Equation
  19. Bellman Optimality Equation
  20. Cauchy Sequence and Green's Equation
  21. Banach Fixed Point Theorem
  22. Convergence Proof
  23. Lpi Convergence
  24. Value Iteration
  25. Policy Iteration
  26. Dynamic Programming
  27. Monte Carlo
  28. Control in Monte Carlo
  29. Off Policy MC
  30. UCT
  31. TD(0)
  32. TD(0) Control
  33. Q-Learning
  34. Afterstate
  35. Eligibility Traces
  36. Backward View of Eligibility Traces
  37. Eligibility Trace Control
  38. Thompson Sampling Recap
  39. Function Approximation
  40. Linear Parameterization
  41. State Aggregation Methods
  42. Function Approximation and Eligibility Traces
  43. LSTD and LSTDQ
  44. LSPI and Fitted Q
  45. DQN and Fitted Q-Iteration
  46. Policy Gradient Approach
  47. Actor Critic and REINFORCE
  48. REINFORCE (cont'd)
  49. Policy Gradient with Function Approximation
  50. Hierarchical Reinforcement Learning
  51. Types of Optimality
  52. Semi Markov Decision Processes
  53. Options
  54. Learning with Options
  55. Hierarchical Abstract Machines
  56. MAXQ
  57. MAXQ Value Function Decomposition
  58. Option Discovery
  59. POMDP Introduction
  60. Solving POMDP

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IIT Madras.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights