Pratap Tokekar

Adaptive Conformal Guidance for Learning under Uncertainty

PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning

VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning

On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning

CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems

Sketch-to-Skill: Bootstrapping Robot Learning with Human Drawn Trajectory Sketches

On the Sample Complexity of a Policy Gradient Algorithm with Occupancy Approximation for General Utility Reinforcement Learning