3 papers
cs.LG2026
MARA: Flow-Matching-Guided Multi-Agent Resource Allocation for Computational Resource Efficient Learning
Hanye Zhao, Muning Wen, Yong Yu +1
Allocating limited computation among concurrent learning tasks is difficult when each task must reach a target loss before a deadline but its required training effort is unknown. E…
cs.LG2024
DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning
Hanye Zhao, Xiaoshen Han, Zhengbang Zhu +4
With the great success of diffusion models (DMs) in generating realistic synthetic vision data, many researchers have investigated their potential in decision-making and control. M…
cs.LG2023
Diffusion Models for Reinforcement Learning: A Survey
Zhengbang Zhu, Hanye Zhao, Haoran He +5
Diffusion models surpass previous generative models in sample quality and training stability. Recent works have shown the advantages of diffusion models in improving reinforcement…