# dennybritz/reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

Repository: https://github.com/dennybritz/reinforcement-learning
Canonical: https://ross.abutalabs.com/products/reinforcement-learning
Homepage: http://www.wildml.com/2016/10/learning-reinforcement-learning/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2023-07-13T09:52:27+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3661, "days_push": 1147, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 22116, forks 6122 (observed 2026-08-28T04:11:32.387667+00:00)

## What it is
A collection of Jupyter Notebook implementations, exercises, and solutions for popular reinforcement learning algorithms, designed to accompany Sutton & Barto's textbook and David Silver's course. Code is written in Python 3 using OpenAI Gym environments and TensorFlow for deep RL methods like DQN and actor-critic.

## Use cases
- learn reinforcement learning algorithms with hands-on code
- find solutions to Sutton and Barto textbook exercises
- implement Q-learning and SARSA from scratch
- study deep Q-learning for Atari games
- understand policy gradient and actor-critic methods
- practice with OpenAI Gym environments
- supplement David Silver's RL course with code

## When to choose
- you want worked notebook examples alongside classic RL theory materials
- you need reference implementations of tabular and deep RL algorithms
- you're following Sutton's book or Silver's course and want coding practice

## When to avoid
- you need a production-ready RL library or framework
- you want the latest state-of-the-art algorithms like PPO or SAC
- you need actively maintained code with current dependency versions

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: reinforcement-learning, machine-learning, deep-learning, data-science
- domain: reinforcement-learning, machine-learning, deep-learning, education, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, openai-gym, tensorflow, sutton-barto, david-silver-course, q-learning, policy-gradient, exercises-and-solutions

## Member repositories
- dennybritz/reinforcement-learning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:32.387667+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:57:43.008322+00:00, confidence not recorded.
  - readme: https://github.com/dennybritz/reinforcement-learning (fetched 2026-08-28T04:11:32.387667+00:00, sha fe2ef4fd510e)
  - homepage: http://www.wildml.com/2016/10/learning-reinforcement-learning/ (fetched 2026-08-29T07:55:55.202896+00:00, sha bf86b6172d5a)
- Data as of 2026-08-30T08:39:29.467469+00:00.