Xinsong Feng — accepted AI-conference papers

2026

Offline Reinforcement Learning with Generative Trajectory Policies

Xinsong Feng, Leshu Tang, Chenan Wang, Haipeng Chen

ICML 2026poster

Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models like diffusion policies are computationally expensive, while…

Cited by 0 Source ↗Scholar ↗

2025

Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning

Xinsong Feng, Zihan Yu, Yanhai Xiong, Haipeng Chen

ICLR 2025poster

Reinforcement learning (RL) has emerged as a promising tool for combinatorial optimization (CO) problems due to its ability to learn fast, effective, and generalizable solutions. Nonetheless, existing works mostly focus on one-shot deterministic CO, while sequential stochastic CO (SSCO) has rarely…

Cited by 0 Source ↗PDF ↗Scholar ↗