Xinran Li

MAGE: Multi-scale Autoregressive Generation for Offline Reinforcement Learning

Getting Your LLMs Ready for Reinforcement Learning with Lightweight SFT

GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL

Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning

Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective

C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning