← Back to Benchmarks
simmediumsim-to-realmetric · varies
Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning
Description
Reinforcement learning in massively parallel physics simulations has driven major progress in sim-to-real robot learning. However, current approaches remain brittle and task-specific, relying on extensive per-task engineering to design rewards, curricula, and demonstrations. Even with this engineering, they often fail on long-horizon, contact-rich manipulation tasks and do not meaningfully scale with compute, as performance quickly saturates when training revisits the same narrow regions of stat