Dongge Han

Dongge Han

Doctoral Student

Student, Balliol College

Leaving date: 4th May 2022

Themes:

• Artificial Intelligence and Machine Learning

See Also:

• Personal Webpage

Interests

Reinforcement Learning, Multiagent Systems, Game Theory

Biography

I am a PhD in Computer Science (thesis defended) at the University of Oxford, supervised by Prof. Michael Wooldridge and Prof. Alex Rogers . My research interests include Multiagent Reinforcement Learning, Hierarchical Reinforcement Learning and Game Theory. In particular, my thesis studies Game-theoretic Payoff Allocation in Multiagent Machine Learning Systems.

Prior to my PhD, I obtained an MSc in Computer Science (Graduated with Distinction, 2016) from the University of Oxford. I obtained a BSc in Physics with a Minor Degree in IT (First class honours, 2015) from the Hong Kong University of Science and Technology. I was an exchange student at EPFL (Spring 2014).

During my PhD, I was a Research Intern (Machine Learning) at Microsoft Research Cambridge (Summer 2019) where I was supervised by Dr. Sebastian Tschiatschek. I was  a Machine Learning Intern (Natural Language Processing) at Apple Siri Cambridge (Summer 2017) where I was supervised by Dr. Thomas Voice.

Please find more details on my personal homepage. I am graduating around May 2022 and am actively seeking full time opportunities. Please feel free to contact me via email.

Selected Publications

View AllManage publications

• Multiagent Model−based Credit Assignment for Continuous Control

  Dongge Han‚ Chris Xiaoxuan Lu‚ Tomasz P. Michalak and Michael Wooldridge

  f. 2021.

  Details about Multiagent Model−based Credit Assignment for Continuous Control | BibTeX data for Multiagent Model−based Credit Assignment for Continuous Control

• Replication−Robust Payoff−Allocation for Machine Learning Data Markets

  Dongge Han‚ Michael Wooldridge‚ Alex Rogers‚ Shruti Tople‚ Olga Ohrimenko and Sebastian Tschiatschek

  2020.

  Details about Replication−Robust Payoff−Allocation for Machine Learning Data Markets | BibTeX data for Replication−Robust Payoff−Allocation for Machine Learning Data Markets

• Multi−Agent Hierarchical Reinforcement Learning with Dynamic Termination

  Dongge Han‚ Wendelin Boehmer‚ Michael Wooldridge and Alex Rogers

  2019.

  Details about Multi−Agent Hierarchical Reinforcement Learning with Dynamic Termination | BibTeX data for Multi−Agent Hierarchical Reinforcement Learning with Dynamic Termination

Supervisors