Generalizable Dense Reward for Long-Horizon Robotic Tasks
VLLR is a dense reward framework for long-horizon robotics that combines extrinsic semantic supervision with intrinsic policy certainty. It uses LLMs and VLMs to decompose tasks into subgoals and estimate progress, while an intrinsic reward based on policy self-certainty guides local action refinement. This hierarchical design improves performance on complex, long-horizon tasks.