activity
20242026
collaborators

5 papers

cs.LG2026

OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning

Yu Li, Rui Miao, Tian Lan +1

Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a single trajectory-level advanta…

cs.AI2026

ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning

Yu Li, Rui Miao, Zhengling Qi +1

The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem inst…

stat.ML2025

A Principled Path to Fitted Distributional Evaluation

Sungee Hong, Jiayi Wang, Zhengling Qi +1

In reinforcement learning, distributional off-policy evaluation (OPE) focuses on estimating the return distribution of a target policy using offline data collected under a differen…

stat.ML2025

Distributional Off-policy Evaluation with Bellman Residual Minimization

Sungee Hong, Zhengling Qi, Raymond K. W. Wong

We study distributional off-policy evaluation (OPE), of which the goal is to learn the distribution of the return for a target policy using offline data generated by a different po…

math.ST2024

A Fine-grained Analysis of Fitted Q-evaluation: Beyond Parametric Models

Jiayi Wang, Zhengling Qi, Raymond K. W. Wong

In this paper, we delve into the statistical analysis of the fitted Q-evaluation (FQE) method, which focuses on estimating the value of a target policy using offline data generated…