Qianchuan Zhao

Risk-Sensitive Reinforcement Learning for Alleviating Exploration Dilemmas in Large Language Models

PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier

GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent System

Heterogeneous Graph Temporal Fusion Transformer for Time Series Forecasting in Multi-Domain Physical Systems

Episodic Novelty Through Temporal Distance

DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning

Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset

Maximum Next-State Entropy for Efficient Reinforcement Learning