Calendar

Week 1

Jan 8
Lecture Slides
Course Overview
Readings
Chapter 1 of RLForFinanceBook
Jan 9
Optional
Python Session (Time/Location TBD)
Jan 10
Lecture Slides
Guided Tour of Chapter 3: Markov Process and Markov Reward Process
Readings
Chapter 3 of RLForFinanceBook
Assignment
Assignment 0: Course Setup, Very Easy! Due Jan 12 11:59pm

Week 2

Jan 15
Lecture Slides
Markov Decision Processes (MDP), Value Functions, and Bellman Equations
Readings
Chapter 4 of RLForFinanceBook (Section on POMDP not exam-able)
Jan 17
Lecture Slides
Dynamic Programming Algorithms
Readings
Chapter 5 of RLForFinanceBook
Assignment
Assignment 1: Due Jan 21 11:59pm

Week 3

Jan 22
Lecture Slides
Function Approximation and Approximate Dynamic Programming Algorithms
Readings
Chapter 6 of RLForFinanceBook
Optional
Appendix F of RLForFinanceBook
Jan 24
Lecture Slides
Understanding Risk-Aversion through Utility Theory (as a pre-req for Finance Applications)
Readings
Chapter 7 of RLForFinanceBook
Optional
Appendix A and C of RLForFinanceBook

Week 4

Jan 29
Lecture Slides
Application Problem 1 - Dynamic Asset-Allocation and Consumption
Readings
Chapter 8 of RLForFinanceBook
Optional
Optional: Appendix B, C, and D of RLForFinanceBook; Some (rough) pointers on Discrete versus Continuous MDPs, and solution techniques
Jan 31
Lecture Slides
Application Problems 2 and 3 - Optimal Exercise of American Options and Optimal Hedging of Derivatives in Incomplete Markets
Readings
Intro to Derivatives section in Chapter 9 of RLForFinanceBook
Optional
Appendix C and E of RLForFinanceBook; Derivatives Pricing Theory in Chapter 9 of RLForFinanceBook (Derivatives Pricing Theory is not exam-able); Relevant sections in Chapter 9 of RLForFinanceBook for Optimal Exercise and Optimal Hedging in Incomplete Markets; Foundations of Arbitrage-Free and Complete Markets
Assignment
Assignment 2: Due Feb 4 11:59pm

Week 5

Feb 5
Lecture Slides
Application Problem 4 - Optimal Trade Order Execution
Readings
Optimal Trade Order Execution section in Chapter 10 of RLForFinanceBook
Feb 7
Lecture Slides
RL for Prediction (Monte-Carlo and Temporal-Difference)
Readings
MC and TD sections in Chapter 11 of RLForFinanceBook

Week 6

Feb 12
Lecture Slides
RL for Prediction (Eligibility Traces and TD(Lambda))
Readings
Eligibility Traces and TD(Lambda) sections in Chapter 11 of RLForFinanceBook
Feb 14
Lecture Slides
RL for Prediction (Eligibility Traces and TD(Lambda))
Readings
Eligibility Traces and TD(Lambda) sections in Chapter 11 of RLForFinanceBook

Week 7

Feb 19
Lecture Slides
RL for Control (Optimal Value Function/Optimal Policy)
Readings
Chapter 12 of RLForFinanceBook
Feb 21
Lecture Slides
Batch RL, Experience-Replay, DQN, LSPI
Readings
Sections 13.1 to 13.6 in Chapter 13 of RLForFinanceBook
Feb 23
Assignment
Assignment 3: Due Feb 23 11:59pm

Week 8

Feb 26
Lecture Slides
Value Function Geometry and Gradient TD
Readings
Sections 13.7 and 13.8 in Chapter 13 of RLForFinanceBook
Feb 28
Lecture Slides
Policy Gradient Algorithms
Readings
Chapter 14 of RLForFinanceBook
Exam
Timing
February 28 @ 8:00 PM PST - March 2 @ 8:00 PM PST (48 Hours)
Logistics
Take home exam, to be completed individually and in compliance with the honor code, submitted via Gradescope

Week 9

Mar 5
Lecture Slides
Exploration versus Exploitation (Multi-Armed Bandits)
Readings
Chapter 15 of RLForFinanceBook
Mar 7
Lecture Slides
Blending Learning and Planning, Planning & Control for Inventory & Pricing
Readings
Chapter 16 of RLForFinanceBook + Bonus Topic

Week 10

Mar 12
Guest Lecture (TBD)
Mar 14
Final Project Presentations (Class extended from 4:30pm to 7:00pm)