JAEarly / Reinforcement_Learning_An_Introduction_Ed2_Solutions

My solutions to the exercises in the second edition (2018) of Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto.

Reinforcement_Learning_An_Introduction_Ed2_Solutions

My solutions to the exercises in the second edition (2018) of Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto. This is an on-going project to complete all the exercises for each chapter of the book, and also reimplement examples where useful. While the book is not yet published, a near-final draft is available online here.

Format

The main write-up is in Latex, with programming solutions done in Python. The work is grouped by chapter, with the master document solutions.tex in the root directory. A complied version of the Latex document is also included for ease of use, see solutions.pdf.

Contribution

If you find mistakes or have any questions, please open an Issue so it can be properly tracked and seen by other users. If you would like to contribute new solutions or improve existing ones, please open a Pull Request.

Progress

• Chapter 1
• Chapter 2
• Chapter 3
• Chapter 4
• Chapter 5
• Chapter 6
• Chapter 7
• Chapter 8
• Chapter 9
• Chapter 10
• Chapter 11
• Chapter 12
• Chapter 13
• Chapter 14
• Chapter 15
• Chapter 16
• Chapter 17