# keras-rl/keras-rl

Deep Reinforcement Learning for Keras.

Repository: https://github.com/keras-rl/keras-rl
Canonical: https://ross.abutalabs.com/products/keras-rl
Homepage: http://keras-rl.readthedocs.io/
Language: Python
License: MIT
License Family: permissive
Topics: keras, tensorflow, theano, reinforcement-learning, neural-networks, machine-learning
Last push: 2023-09-17T12:33:41+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3714, "days_push": 1081, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5547, forks 1344 (observed 2026-08-28T04:09:22.277516+00:00)

## What it is
A Python library implementing state-of-the-art deep reinforcement learning algorithms (DQN, DDPG, SARSA, and more) that integrates seamlessly with Keras and works out of the box with OpenAI Gym environments. It allows easy extension of agents and environments via simple abstract classes.

## Use cases
- train a DQN agent on an OpenAI Gym environment
- implement deep reinforcement learning with Keras
- experiment with DDPG for continuous control tasks
- learn reinforcement learning algorithms with runnable examples
- build custom RL agents and environments in Python

## When to choose
- you want ready-made deep RL algorithms integrated with Keras
- you are prototyping RL agents against OpenAI Gym environments
- you need a simple, extensible codebase for learning or research in deep RL

## When to avoid
- you need cutting-edge algorithms like PPO or A3C, which are not implemented
- you require actively maintained support for the latest TensorFlow/Keras versions
- you need high-performance, production-scale RL training

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, reinforcement-learning, deep-learning
- domain: reinforcement-learning, machine-learning, deep-learning
- platform: python
- tags: keras, tensorflow, openai-gym, dqn, ddpg, reinforcement-learning-algorithms

## Member repositories
- keras-rl/keras-rl (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:22.277516+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 2026-08-29T17:55:40.618335+00:00, confidence not recorded.
  - readme: https://github.com/keras-rl/keras-rl (fetched 2026-08-28T04:09:22.277516+00:00, sha 97162e5da596)
  - registry_pypi: https://pypi.org/pypi/keras-rl/json (fetched 2026-08-29T08:51:27.875329+00:00, sha 7f862c6b0714)
- Data as of 2026-08-30T08:39:29.467469+00:00.