CSCI 2951-F
Learning and Sequential Decision Making

Meeting Schedule

Important notes:
Date Topic Homework Slides Supplemental Material
01/25/24 Introduction Read chapter 1 intro SB chapter 1
ML's slides
01/30/24 Probability and Simple Decisions Read chapters 2 and 6 probability
decisions
ML's slides
Foundations of Computer Science Sections 4.9-4.12
02/01/24 Algorithms for MDPs Read chapter 7 mdp SB chapters 3 and 4
ML's slides
02/06/24 Catch up
02/08/24 Approximations and Search Read chapters 8 and 9
HW1 assigned, due 2/15
ApproxVI
TreeSearch
ML's slides
Stable Function Approximation in Dynamic Programming
02/13/24 Catch up
02/15/24 Model Free RL Read chapter 17 ModelFreeRL SB chapter 6
ML's slides
02/20/24 Break
02/22/24 Advanced Model Free RL Read Human Level Control Through Deep Reinforcement Learning DeepRL SB Chapter 9
David Silver's Slides
02/27/24 Bandits Read chapter 15
HW2 assigned, due 3/12/24
bandits SB Chapter 2
ML slides
Introduction to Multi-Armed Bandits by Aleksandrs Slivkins
02/29/24 Model Based Reinforcement Learning Read chapter 16 ModelBasedRL ML's slides
03/05/24 Sarsa, Lambda Read chapters 10 and 11 SB Chapters 7,12
03/07/24 Policy Search PolicySearch ML's slides
03/12/24 Policy Gradient Read chapters 12 and 13 PGinPractice ML's slides
03/14/24 Finish Policy Gradient, Review Linear Programs LPs
03/19/24 Learning From Demonstration Read Chapter 18
HW3 assigned, due 4/4/24
LfD ML Slides
03/21/24 Reproducibility, Shaping and Catch up Read chapture 17.5, Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping, reproducibility
shaping
Potential Shaping and Q-value Initialization are Equivalent
Measuring the Reliability of Reinforcement Learning Algorithms
03/26/24 Spring Break
03/28/24 Spring Break
04/02/24 Hidden Markov Models and Particle Filters Read chapter 19 HMMs
04/04/24 Catch up Particle Filters
04/09/24 POMDP basics Read chapters 19 and 20 POMDPs POMDPs for Dummies
ML's slides
04/11/24 POMDPs (approximate solutions) Read chapters 21, 22 and 23 POMDP approximations
04/16/24 Matrix Games Read chapter 24
HW4 assigned, due 4/25
games ML's slides
04/18/24 Finish Matrix Games Read chapter 25
04/23/24 Markov Games Read chapter 26, 27 MarkovGames MARL ML's slides
04/25/24 - 05/07/24 Catch up, extra topics (abstraction, hierarchy, etc.), projects AllTheOtherThings