Yiming Ye

About

Yiming Ye’s research lies at the intersection of artificial intelligence, decision-making systems, and energy management, with a focus on bridging knowledge representation and reinforcement learning. In his early work, “Knowledge granularity and action selection” (1998), Ye explored how varying levels of knowledge abstraction can guide efficient action selection in intelligent agents—a foundational idea that has influenced subsequent work in hierarchical reasoning and autonomous control. More recently, Ye has advanced the application of deep reinforcement learning to real-world engineering challenges. His 2023 paper introduces an innovative approach that uses decision trees to provide an expert-knowledge warm start for deep reinforcement learning, specifically targeting energy management in hybrid electric vehicles. This method significantly reduces training time while improving policy quality, addressing a critical bottleneck in deploying RL in practical systems. Though citation counts for these works are modest, Ye’s contributions are notable for their conceptual depth and practical relevance, demonstrating how classical AI concepts can be revitalized to solve pressing modern problems in sustainable transportation and intelligent control.

Research Focus

Key Achievements

Top Papers

1. 1
   Knowledge granularity and action selection

   3 citations · 1998
2. 2
   Automated Expert Knowledge-Based Deep Reinforcement Learning Warm Start via Decision Tree for Hybrid Electric Vehicle Energy Management

   1 citations · 2023

Key Collaborators

Contact & Links