Shangtong Zhang

Reward Is Enough: LLMs Are In-Context Reinforcement Learners

The Stability and Convergence of Two-Timescale Stochastic Approximation with Markovian Noise for Reinforcement Learning

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

Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set

Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning

Revisiting a Design Choice in Gradient Temporal Difference Learning

Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning

Towards Provable Emergence of In-Context Reinforcement Learning

Doubly Optimal Policy Evaluation for Reinforcement Learning

Almost Sure Convergence of Average Reward Temporal Difference Learning