Hanhan Zhou

Hi! 👋

This is Hanhan, currently an Applied Scientist at AWS AI Labs with a focus on LLM agents, planning and resoning.

Previously I obtained my Ph.D from the the George Washington University, where I worked at the department of ECE and in the Lab for Intelligent Networking and Computing. I’m fortunate and grateful to be advised by Prof.Tian Lan and worked with Prof.Vaneet Aggarwal and Prof.Guru Venkataramani.

I’m interested in Reinforcement Learing, Federated Learning and Generative Models. My research endeavors have predominantly centered around the design and optimization of decentralized multi-agent reinforcement learning algorithms. This work entails the development of sophisticated methodologies for coordinating agent actions in complex environments without centralized control. Additionally, I have explored the application of reinforcement learning in the domain of network resource allocation to enhance efficiency and performance in distributed systems.

Furthermore, my academic pursuits have included the investigation of heterogeneous federated learning algorithms and their optimizations. In this topic, my focus has been on the optimization of these algorithms to address the challenges posed by the nature of heterogeneous models in distributed environments.

Lastly, my research portfolio also encompasses the domain of offline reinforcement learning, with a particular focus on utilizing sequence generative modeling. This area of study involves the development of generative models that can effectively learn from datasets without interaction with the environment, an approach that holds substantial promise for advancing the field of reinforcement learning by mitigating the dependency on extensive online data collection.

Please contact me if you would like to collaborate on research projects or other opportunities, thank you!