Repository
Open source
Gymnasium · Farama-Foundation
Standard environment API and reference environments for reinforcement learning.
Robot learning frameworks
Benchmarks / Research
Meta-World
A manipulation benchmark for multi-task and meta-learning experiments.
Overview
A manipulation benchmark for multi-task and meta-learning experiments.
Compare task definitions, evaluation splits, metrics and environment versions. Results from different robot configurations or protocols are not directly comparable.
Project information
- Maintainer
- Farama-Foundation
- Primary language
- Python
- Repository code license
- MIT
- Model-weight license
- Not recorded
- Dataset license
- Not recorded
- Hardware design license
- Not recorded
- Maintenance
- Not archived in the last recorded metadata
- Last observed repository push
- 2026-09-12
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Documentation sections
- Installation
- API
- Available Benchmarks
- Multi-Task Benchmarks
- Meta-Learning Benchmarks
- Creating Multi-Task Benchmarks
Browse this resource’s categories
Application areas
Education & research ↗Explore related collections
Browse Benchmarks →More in Benchmarks
Repository
Open source