| Date
|
Topic
|
Assignments
|
|
Aug. 28
| No Class -- but Reading Assignment
| Chapter 1
Chapter 2
|
|
Sept. 4
| The Basics of Reinforcement Learning
| Chapter 3
|
|
Sept. 11
| Dynamic Programming
| Chapter 4
|
|
Sept. 18
| Monte Carlo Methods
| Chapter 5
|
|
Sept. 25
| Temporal Difference Learning
| Chapter 6
|
|
Oct. 2
| Eligibility Traces
| Chapter 7
|
|
Oct. 9
| Generalization and Function Approximation
| Chapter 8
Paper {1}
|
|
Oct. 16
| Planning and Learning
| Chapter 9
|
|
Oct. 23
| Policy Gradient Methods I
| Papers {1}{2}{3},
optional {4}{5}
|
|
Oct. 30
| No class
|
|
|
Nov. 6
| Policy Gradient Methods II
| Papers {1}
|
|
Nov. 13
| Partially Observable Reinforcement Learning Problems
| Paper {1}
|
|
Nov. 20
| Hierarchical Reinforcement Learning
| Paper {1}
|
|
Nov. 27
| Higher Level Actions, Abstraction, Action Primitives, Options
| Paper {1}
|
|
Dec. 4
| Project Presentations
|
|
