# chainer/chainerrl

ChainerRL is a deep reinforcement learning library built on top of Chainer.

Repository: https://github.com/chainer/chainerrl
Canonical: https://ross.abutalabs.com/products/chainerrl
Language: Python
License: MIT
License Family: permissive
Topics: chainer, reinforcement-learning, deep-learning, machine-learning, python, dqn, actor-critic
Last push: 2021-08-10T18:25:48+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3502, "days_push": 1849, "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 1198, forks 225 (observed 2026-08-28T04:03:57.643619+00:00)

## What it is
ChainerRL is a deep reinforcement learning library implementing state-of-the-art algorithms like DQN, Rainbow, PPO, SAC, and A3C in Python on top of the Chainer deep learning framework. It includes examples for Atari 2600 and OpenAI Gym environments.

## Use cases
- train deep reinforcement learning agents
- implement dqn or rainbow in python
- run a3c async training on atari
- experiment with ppo and sac algorithms
- reproduce rl research results
- learn reinforcement learning with gym environments

## When to choose
- you are already using the Chainer framework
- you need CPU asynchronous training algorithms like A3C or ACER
- you want a wide selection of classic deep RL algorithms in one library

## When to avoid
- you prefer PyTorch - use PFRL, the maintained successor instead
- you need actively maintained software with recent updates
- you need GPU-first batch training on modern hardware

## Facets
- artifact type: library
- maturity: maintenance
- function: reinforcement-learning, deep-learning, machine-learning
- domain: reinforcement-learning, machine-learning, deep-learning
- platform: python
- tags: chainer, dqn, actor-critic, ppo, sac, a3c, gym, atari, deep-reinforcement-learning, linux, macos

## Member repositories
- chainer/chainerrl (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:57.643619+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 2026-08-30T06:21:09.055502+00:00, confidence not recorded.
  - readme: https://github.com/chainer/chainerrl (fetched 2026-08-28T04:03:57.643619+00:00, sha 5fef23e9b3e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.