5 papers
TSC: Topology-Conditioned Stackelberg Coordination for Multi-Agent Reinforcement Learning in Interactive Driving
Xiaotong Zhang, Gang Xiong, Yuanjing Wang +3
Safe and efficient autonomous driving in dense traffic is fundamentally a decentralized multi-agent coordination problem, where interactions at conflict points such as merging and…
Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
Jie Cheng, Ruixi Qiao, Yingwei Ma +5
A significant aspiration of offline reinforcement learning (RL) is to develop a generalist agent with high capabilities from large and heterogeneous datasets. However, prior approa…
Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
Jie Cheng, Gang Xiong, Ruixi Qiao +5
Process reward models (PRMs) have proven effective for test-time scaling of Large Language Models (LLMs) on challenging reasoning tasks. However, reward hacking issues with PRMs li…
SUMO-MCP: Leveraging the Model Context Protocol for Autonomous Traffic Simulation and Optimization
Chenglong Ye, Gang Xiong, Junyou Shang +3
Traffic simulation tools, such as SUMO, are essential for urban mobility research. However, such tools remain challenging for users due to complex manual workflows involving networ…
RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences
Jie Cheng, Gang Xiong, Xingyuan Dai +3
Preference-based Reinforcement Learning (PbRL) circumvents the need for reward engineering by harnessing human preferences as the reward signal. However, current PbRL methods exces…