Rohan Chandra

Reward Is Enough: LLMs Are In-Context Reinforcement Learners

Efficient and Robust Behavior Policy Search for Online Off-policy Evaluation through Transition Gradients

Safe In-Context Reinforcement Learning

Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features

Towards Provable Emergence of In-Context Reinforcement Learning

IndianRoad: A Video Dataset of Diverse Atomic Visual Elements in Dense and Unpredictable Environments