Ting-Han Fan

Siemens (United States)

Papers

1

Total Citations

11

H-Index

1

About

Ting-Han Fan is a researcher advancing reinforcement learning (RL) for real-world industrial applications, with a focus on bridging algorithmic theory and practical deployment. His key research areas include reinforcement learning, integer-action spaces, and scalable decision-making under high-dimensional constraints. Fan’s most notable contribution is his work on "Soft Actor-Critic With Integer Actions" (2022, 11 citations), which tackles the challenging problem of applying RL to integer action spaces—a setting common in industry but notoriously difficult due to combinatorial explosion and high dimensionality. By integrating the Soft Actor-Critic (SAC) algorithm with tailored techniques, Fan provides a principled framework for efficient exploration and policy optimization in this domain, offering a practical solution for problems like resource allocation and scheduling. His work stands out for its direct relevance to industrial deployment, where discrete integer actions are the norm. Fan’s research demonstrates a keen ability to adapt state-of-the-art RL methods to constrained, real-world settings, making his contributions valuable for both academics and practitioners seeking to deploy RL in complex operational environments.

Research Focus

Key Achievements

1
H-Index
1
Papers
11
Total Citations
11
Avg Citations/Paper
🏆 Most Cited Paper
Soft Actor-Critic With Integer Actions
11 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 1
🏛 Institutions: Siemens (United States)

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago