obsidian6s/deep-rl-notes

A collection of comprehensive notes on Deep Reinforcement Learning, customized for UC Berkeley's CS 285 (prev. CS 294-112)

Deep Reinforcement Learning Textbook

A collection of comprehensive notes on Deep Reinforcement Learning, based on UC Berkeley's CS 285 (prev. CS 294-112) taught by Professor Sergey Levine.

• Compile the latex source code into PDF locally.
• Please let me know if you have any questions or suggestions. Reach me via [email protected]

Update Log (Will stop updating until Oct. 31 because of ICRA 2021)

• Aug 26, 2020: Started adding Fall 2020 materials
• Aug 28, 2020: Fixed typos in Intro. Credit: Warren Deng.
• Aug 30, 2020: Added more explanation to the imitation learning chapter.
• Sep 13, 2020: Added advanced PG in PG and fixed typos in PG.
• Sep 14, 2020: AC chapter format, typos fix, more analysis on A2C
• Sep 16, 2020: Chapter 10.1 KL div typo fix. Credit: Cong Wang.
• Sep 19, 2020: Chapter 3.7.1 parathesis typo fix. Credit: Yunkai Zhang.
• Sep 23, 2020: Q learning chapter fix
• Sep 26, 2020: More explanation and fix to the advanced PG chapter (specifically intuition behind TRPO).
• Sep 28, 2020: Typo fixed and more explanation in Optimal Control. Typos were pointed out in Professor Levine's lecture.
• Oct 6, 2020: Model-based RL chapter fixed. Added Distillation subsection.
• Nov. 20, 2020: Fixed typos in DDPG, Online Actor Critic, and PG theory. Credit: Javier Leguina.