Yuanheng Zhu

Empowering Multi-Robot Cooperation via Sequential World Models

R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

Learning and Planning Multi-Agent Tasks via an MoE-based World Model

Divergence-Regularized Discounted Aggregation: Equilibrium Finding in Multiplayer Partially Observable Stochastic Games

Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games

INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement Learning

Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium

DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy

Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning

Constrained Exploitability Descent: Finding Mixed-Strategy Nash Equilibrium by Offline Reinforcement Learning