Farama-Foundation/D4RL resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1700 stars · 308 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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• requiring PyBullet or Flow tasks, which are no longer maintained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

dataset · maturity maintenance

machine-learning reinforcement-learning simulation benchmarking reinforcement-learning machine-learning robotics python offline-rl benchmark mujoco gymnasium datasets farama linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Farama-Foundation/D4RL")