admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-20 11:09:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'docs/adding-benchmarks-guide' into refactor/benchmark-dispatch

Browse Source
This commit is contained in:
Pepijn
2026-04-03 13:56:49 +02:00
parent 6f2823bfc4 90e614f6b9
commit 89ce91f69f
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/source/metaworld.mdx
+8 -8
View File
@@ -2,7 +2,7 @@
Meta-World is an open-source simulation benchmark for **multi-task and meta reinforcement learning** in continuous-control robotic manipulation. It bundles 50 diverse manipulation tasks using everyday objects and a common tabletop Sawyer arm, providing a standardized playground to test whether algorithms can learn many different tasks and generalize quickly to new ones. Meta-World is an open-source simulation benchmark for **multi-task and meta reinforcement learning** in continuous-control robotic manipulation. It bundles 50 diverse manipulation tasks using everyday objects and a common tabletop Sawyer arm, providing a standardized playground to test whether algorithms can learn many different tasks and generalize quickly to new ones.
- Paper: [Meta-World+: An Improved, Standardized, RL Benchmark](https://arxiv.org/abs/1910.10897) - Paper: [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning paper](https://arxiv.org/abs/1910.10897)
- GitHub: [Farama-Foundation/Metaworld](https://github.com/Farama-Foundation/Metaworld) - GitHub: [Farama-Foundation/Metaworld](https://github.com/Farama-Foundation/Metaworld)
- Project website: [metaworld.farama.org](https://metaworld.farama.org) - Project website: [metaworld.farama.org](https://metaworld.farama.org)
@@ -12,13 +12,13 @@ Meta-World is an open-source simulation benchmark for **multi-task and meta rein
Meta-World provides 50 tasks organized into difficulty groups. In LeRobot, you can evaluate on individual tasks, difficulty groups, or the full MT50 suite: Meta-World provides 50 tasks organized into difficulty groups. In LeRobot, you can evaluate on individual tasks, difficulty groups, or the full MT50 suite:
| Group | CLI name | Tasks | Description | | Group | CLI name | Tasks | Description |
| ---------- | -------------------- | ------ | ------------------------------------------------------ | | ---------- | -------------------- | ----- | ------------------------------------------------------ |
| Easy | `easy` | Subset | Tasks with simple dynamics and single-step goals | | Easy | `easy` | 28 | Tasks with simple dynamics and single-step goals |
| Medium | `medium` | Subset | Tasks requiring multi-step reasoning | | Medium | `medium` | 11 | Tasks requiring multi-step reasoning |
| Hard | `hard` | Subset | Tasks with complex contacts and precise manipulation | | Hard | `hard` | 6 | Tasks with complex contacts and precise manipulation |
| Very Hard | `very_hard` | Subset | The most challenging tasks in the suite | | Very Hard | `very_hard` | 5 | The most challenging tasks in the suite |
| MT50 (all) | Comma-separated list | 50 | All 50 tasks — the most challenging multi-task setting | | MT50 (all) | Comma-separated list | 50 | All 50 tasks — the most challenging multi-task setting |
You can also pass individual task names directly (e.g., `assembly-v3`, `dial-turn-v3`). You can also pass individual task names directly (e.g., `assembly-v3`, `dial-turn-v3`).