Yunhao Tang

Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards

Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics

Optimizing Language Models for Inference Time Objectives using Reinforcement Learning

On scalable oversight with weak LLMs judging strong LLMs

A Distributional Analogue to the Successor Representation

Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model