Jia-Yue Su

Harnessing VLM in Embodied RL: From Reward Regressor to Success Detector via Exploration-Augmented Key-Observation Gating

The proposed exploration-augmented key-observation gating first determines whether the current RL episode is judgment-worthy based on its similarity to a generated success trajectory, and proposes VLM success reward via Exploration-Augmented Key-Observation Gating (VLMeg) to well harness VLM for embodied reward design.