This repository contains my personal Sutton & Barto exercise solutions. Each subfolder contains a pdf file with questions and answers and python scripts for programming exercises.
Solutions are for personnel reference. No guarantee of correctness is provided.
Corrections are welcome...
I also created rl-algo repository for RL Control algorithm implementations.
- Chapter 2
- Chapter 3
- Chapter 4
- Chapter 5
- Chapter 6
- Chapter 7
- Chapter 8
- Chapter 9
- Chapter 10
- Chapter 11
- Chapter 12
- Chapter 13
If you are interested in Deep RL, check out the Berkeley YouTube Deep RL course by Sergey Levine. The course is a precious resource. You can also refer to my solutions to the course assignments at Berkeley RL Homework Answers.
If you are interested in Meta-RL, check out the Standford YouTube Meta Learning course by Chealse Finn. The course is a precious resource. You can also refer to my solutions to the course assignments at Standford Meta Learning Homework Answers.
All solutions belong to me.
I need to credit the following authors.
I leveraged the great work of vojtamolda to verify my solutions:
I leveraged the great work of ShangtongZhang to improve may solutions to programming exercises. Sometimes I just used a modified version of his work. Credits are kept.
Please prefer the mentioned works over mine.