# Farama-Foundation/D4RL

A collection of reference environments for offline reinforcement learning

Repository: https://github.com/Farama-Foundation/D4RL
Canonical: https://ross.abutalabs.com/products/d4rl
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-11-18T16:40:39+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": 2334, "days_push": 653, "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 1700, forks 308 (observed 2026-08-28T04:05:24.258693+00:00)

## What it is
D4RL is an open-source benchmark providing standardized environments and datasets for offline reinforcement learning research. It is now in maintenance mode, with its environments and datasets migrated to Gymnasium, Gymnasium-Robotics, and Minari.

## Use cases
- benchmark offline reinforcement learning algorithms
- get standardized RL datasets for training agents
- evaluate offline RL methods on MuJoCo tasks
- compare offline RL research results against a common baseline
- download demonstration datasets for batch RL experiments

## When to choose
- reproducing published offline RL papers that use D4RL benchmarks
- needing legacy environments and datasets for existing research code

## When to avoid
- starting a new offline RL project (use Minari and Gymnasium instead)
- needing actively maintained environments or new Python version support
- requiring PyBullet or Flow tasks, which are no longer maintained

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, reinforcement-learning, simulation, benchmarking
- domain: reinforcement-learning, machine-learning, robotics
- platform: python
- tags: offline-rl, benchmark, mujoco, gymnasium, datasets, farama, linux, macos

## Member repositories
- Farama-Foundation/D4RL (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:24.258693+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 2026-08-30T03:37:44.844978+00:00, confidence not recorded.
  - readme: https://github.com/Farama-Foundation/D4RL (fetched 2026-08-28T04:05:24.258693+00:00, sha 58a5031ba5a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.