manipulation · benchmark suite
Meta-World
Multi-task and meta-reinforcement-learning benchmark suite with versioned MT and ML protocols.
verifiedAug 20, 2026Store MT or ML protocol, task split, goals, adaptation procedure, package version, and generation.
Evaluation setting
simulation
Primary metric
Average task success rate
Source count
4 bound primary sources
Provenance
Primary sources
Found an update or correction?
Submissions enter a private review queue and never change the public registry automatically.
Suggest a correction