manipulation · benchmark suite
LIBERO
Lifelong robot-learning benchmark with four suites and 130 tasks.
verifiedAug 20, 2026Store paper revision, repository/data version, task order, and checkpoint protocol with results.
Evaluation setting
simulation
Primary metric
Forward Transfer
Source count
3 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