this is work that goes along with a book that is a work in progess.

Denny Britz 59cded5174 Merge pull request #199 from anuzis/master 2 weeks ago
DP a35df15268 Updated links to new version of Sutton's book 1 month ago
DQN 4a2df43bb1 fixed shape descriptions for neural network input layer 1 month ago
FA a35df15268 Updated links to new version of Sutton's book 1 month ago
Introduction a35df15268 Updated links to new version of Sutton's book 1 month ago
MC a35df15268 Updated links to new version of Sutton's book 1 month ago
MDP a35df15268 Updated links to new version of Sutton's book 1 month ago
PolicyGradient a35df15268 Updated links to new version of Sutton's book 1 month ago
TD 1abaae41f6 Q-Learning docstring improvements. 2 weeks ago
lib 01b8b1379a nit 3 months ago
.gitignore 518a514333 Deep Q Updates 2 years ago
LICENSE 4ef051ba62 Add MIT License 2 years ago
README.md a35df15268 Updated links to new version of Sutton's book 1 month ago
__init__.py 15c739aa02 Add MC Control with Epsilon-Greedy Policies 2 years ago

README.md

Overview

This repository provides code, exercises and solutions for popular Reinforcement Learning algorithms. These are meant to serve as a learning tool to complement the theoretical materials from

Each folder in corresponds to one or more chapters of the above textbook and/or course. In addition to exercises and solution, each folder also contains a list of learning goals, a brief concept summary, and links to the relevant readings.

All code is written in Python 3 and uses RL environments from OpenAI Gym. Advanced techniques use Tensorflow for neural network implementations.

Table of Contents

List of Implemented Algorithms

Resources

Textbooks:

Classes:

Talks/Tutorials:

Other Projects:

Selected Papers: