dennybritz/reinforcement-learning
Python implementations of reinforcement learning algorithms with exercises and solutions for Sutton's textbook and David Silver's RL course.
Not currently ranked — collecting fresh signals.
star history
This repository provides Jupyter Notebook implementations of popular reinforcement learning algorithms including dynamic programming, Monte Carlo methods, temporal difference learning, function approximation, deep Q learning, and policy gradient methods. Code uses OpenAI Gym for environment simulation and Tensorflow for neural network implementations. Each section includes learning goals, concept summaries, and solutions to textbook exercises.
Frequently asked
- What is dennybritz/reinforcement-learning?
- Python implementations of reinforcement learning algorithms with exercises and solutions for Sutton's textbook and David Silver's RL course.
- Is reinforcement-learning open source?
- Yes — dennybritz/reinforcement-learning is open source, released under the MIT license.
- What language is reinforcement-learning written in?
- dennybritz/reinforcement-learning is primarily written in Jupyter Notebook.
- How popular is reinforcement-learning?
- dennybritz/reinforcement-learning has 22.1k stars on GitHub.
- Where can I find reinforcement-learning?
- dennybritz/reinforcement-learning is on GitHub at https://github.com/dennybritz/reinforcement-learning.