# takuseno/d3rlpy

An offline deep reinforcement learning library

Repository: https://github.com/takuseno/d3rlpy
Canonical: https://ross.abutalabs.com/products/d3rlpy
Homepage: https://takuseno.github.io/d3rlpy
Language: Python
License: MIT
License Family: permissive
Topics: deep-reinforcement-learning, deep-learning, pytorch, offline-rl
Last push: 2025-09-10T23:06:16+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 41, release rhythm 40, longevity 100
- inputs: {"age_days": 2293, "days_push": 357, "days_rel": 549, "gap_med": 19.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1679, forks 267 (observed 2026-08-28T04:05:21.056313+00:00)

## What it is
d3rlpy is a Python library for offline and online deep reinforcement learning built on PyTorch, offering state-of-the-art algorithms through a scikit-learn style API. It supports distributional Q functions, data-parallel distributed training, and works with datasets from D4RL, PyBullet, and Atari environments.

## Use cases
- train RL policies from logged datasets without online interaction
- run offline RL experiments on D4RL benchmark datasets
- train online RL agents on gymnasium environments
- scale offline RL training across multiple GPUs or nodes
- reproduce results from offline RL research papers
- apply RL to robotics or medical tasks where online exploration is infeasible

## When to choose
- you need offline RL algorithms like CQL with a simple, well-documented API
- you want both offline and online RL in one library
- you prefer scikit-learn style APIs over writing raw PyTorch training loops
- you need distributed or GPU-accelerated RL training

## When to avoid
- you need a lightweight tabular RL library rather than deep RL
- you require environments or algorithms outside its supported set
- you are locked to an older version and cannot handle v2.x breaking changes

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, reinforcement-learning
- domain: reinforcement-learning, machine-learning, deep-learning
- platform: python, windows
- tags: offline-rl, pytorch, scikit-learn-style-api, distributional-q-function, distributed-training, linux, macos, gpu

## Member repositories
- takuseno/d3rlpy (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:21.056313+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 2026-08-30T03:41:32.284919+00:00, confidence not recorded.
  - readme: https://github.com/takuseno/d3rlpy (fetched 2026-08-28T04:05:21.056313+00:00, sha 216cd48f4d31)
  - homepage: https://takuseno.github.io/d3rlpy (fetched 2026-08-29T11:14:48.963578+00:00, sha de0086963818)
  - registry_pypi: https://pypi.org/pypi/d3rlpy/json (fetched 2026-08-29T11:14:48.972637+00:00, sha f8d30b064722)
- Data as of 2026-08-30T08:39:29.467469+00:00.