Episode Details
Back to EpisodesSARM2 + SPIRAL: Multi-Task Reward Models and RL Refinement for Long-Horizon Dexterous Manipulation
Published 3 months, 1 week ago
Description
Combines scalable autonomous reward modeling with RL-based refinement to improve vision-language-action policies on long-horizon dexterous manipulation tasks via autonomous rollouts. Demonstrates significant gains over imitation learning baselines.