Hang Mike-Wang's Homepage

PhD Candidate School of Electrical and Computer Engineering University of California, Davis Address: Kemper Hall, 545 Bainer Hall Dr, Davis, CA 95616 Email: whang [@] ucdavis [DOT] edu Google Scholar Linkedin (New 2025) Continual RL Book

About Me

I'm a final-year Ph.D student in Electrical and Computer Engineering at UC Davis. I'm fortunate to be advised by Prof. Junshan Zhang and Prof. Yubei Chen (Co-advisor).

My research focuses on developing adaptive embodied AI agents that learn and continually evolve through direct interaction with the physical world (e.g. human feedback). This vision is pursued through three interconnected research areas:

• Warm-start Reinforcement Learning and Self-supervised Learning,

• Multi-agent Reinforcement Learning (distributed optimization), and

• Foundation models (with particular emphasis on World Models).

My work spans both theoretical innovations and practical algorithmic implementations, with applications in autonomous driving, robots, Internet of Things (IoT), and edge computing. I enjoy the interdisciplinary research, such as the use of RL in optical physics (with Prof. Munday), smart grid and biomedical fields.

I am currently seeking academic and research positions. If you would like to learn more about my research, please feel free to contact me.

Education

• Ph.D. student in Electrical Engineering, UC Davis, 2019-2025 (Advisor: Prof. Junshan Zhang, Co-advisor: Prof. Yubei Chen)

• B.Eng (Talent Honor) in Automation, USTC, 2014-2018

Research Experience

• Research Intern, Bosch Center of Artificial Intelligence, Sunnyvale, California, USA, Jun 2024- Dec 2024

  • Project: 1) Adaptive Foundation model through Reinforcement Learning Finetuning for autonomous vehicles; 2) Enhancing motion transformer model with diffusion models through knowledge distillation

  • Mentor: Dr. Burhaneddin Yaman and Dr. Xin Ye

• Research Graduate Intern, Intel, Chandler, Arizona, USA, May 2022 - Aug 2022

  • Project: Reinforcement Learning Aided Chip Manufacture

  • Mentor: Darryl Monteilh, Dr. Manu Shamsa, Dr. Mariano Phielipp (Intel AI Lab)

• Research Engineer, Nanyang Technological University, Singapore, Sep 2018 - Sep 2019

  • Project: P2P Trading in the Smart-Grid Communication Network (EMA Singapore project)

  • Mentor: Prof. Yonggang Wen

• Research Intern, Twente University, Netherlands, July 2017 - Oct 2017

  • Project: Data Fusion For Arm Rehabilitation System

  • Mentor: Prof. ir. B. J. F. van Beijnnum and Mohamed Irfan Mohamed Refai

• Intern, Sensetime, July 2018 - Sep 2018

  • Project: Large-scale distributed Optimization

  • Mentor: Dr. Peng Sun (now with Shanghai AI Lab)

• Research Associate, HI Lab, USTC, June 2016 - Nov 2017

  • Project: Recommender System for drug sensitivity prediction

  • Mentor: Prof. Ao Li

Recent News

• Feb-2025: Our Book “Continual and Reinforcement Learning for Edge AI: Framework, Foundation, and Algorithm Design” will be available to purchase in June 2025 at Springer.com!

• Feb-2025: Our paper on decision making in Human-AI interaction (agentic AI) “Heterogeneous Decision Making: When Uncertainty-aware Planning Meets Bounded Rationality” is accepted by CPAL! See you at Stanford in March!

• Jan-2025: My recent work “AdaWM: Adaptive World Model based Planning for Autonomous Driving” is accepted by ICLR 2025! See you in Singapore.

• May-2024: Our open source platform “CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving” Arxiv is now available!

• Mar-2024: Our work “L-MBOP-E: Latent-Model Based Offline Planning with Extrinsic Policy Guided Exploration” is accepted by IEEE International Conference on Mobility: Operations, Services, and Technologies (MOST), congrats Imran!

• 24-April-2023: Aloha! My work “Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap” is accepted by ICML 2023 (Oral, top 5%). See you in Hawaii!

• 16-May-2022: I start to work as a graduate intern at Intel Network Platform Group and Intel AI lab.

• 28-Sep-2021: My work “Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback” is accepted by NeurIPS 2022.

• 17-Dec-2020: My work Distributed Q-Learning with State Tracking for Multi-agent Networked Control is accepted by AAMAS 2021.

• 27-Oct-2020: Our group's new work System Identification via Meta-Learning in Linear Time-Varying Environments is now available!

Award

• Ph.D. Candidacy Award, UC Davis, 2024

• ICML Oral (Top 5%), 2023

• University Graduate Fellowship, ASU, 2019-2020

• Leadership Fellowship, USTC, 2018

Books

• Continual and Reinforcement Learning for Edge AI: Framework, Foundation, and Algorithm Design

  • Hang Wang, Sen Lin, Junshan Zhang

  • Morgan & Claypool Publishers, 2025

Publications

RL Theory (e.g., Warm-start Reinforcement Learning)

• Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap

  • Hang Wang, Sen Lin, Junshan Zhang

  • ICML 2023 (Oral, Top 5%), Video

• Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback

  • Hang Wang, Sen Lin, Junshan Zhang

  • NeurIPS 2021, Code

• Heterogeneous Decision Making in Mixed Traffic: Uncertainty-aware Planning and Bounded Rationality

  • Hang Wang, Qiaoyi Fang and Junshan Zhang

  • Conference on Parsimony and Learning (CPAL), Stanford, 2025

• Towards Unraveling and Improving Generalization in World Models

  • Qiaoyi Fang, Weiyu Du, Hang Wang and Junshan Zhang

  • CPAL, 2025

• System Identification via Meta-Learning in Linear Time-Varying Environments

  • Sen Lin, Hang Wang, Junshan Zhang

  • arXiv:2010.14664, 2020

Foundation Models and Self-supervised Finetuning

• AdaWM: Adaptive World Model based Planning for Autonomous Driving

  • Hang Wang, Xin Ye, Feng Tao, Chenbin Pan, Abhirup Mallik, Burhaneddin Yaman, Ren Liu and Junshan Zhang

  • ICLR, 2025, Pdf, Code

• Ego-centric Learning of Communicative World Models for Autonomous Driving

  • Hang Wang, Dechen Gao, Qiaoyi Fang and Junshan Zhang

  • Preprint, 2025, Code

• World-Model based Hierarchical Planning with Semantic Communications for Autonomous Driving

  • Dechen Gao, Hang Wang, Shuangyu Cai, Hanchu Zhou, Nejib Ammar, Shatadal Mishra, Iman Soltani and Junshan Zhang

  • Preprint, 2025, Code

• CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving

  • Dechen Gao, Shuangyu Cai, Hanchu Zhou, Hang Wang, Iman Soltani, Junshan Zhang

  • IEEE IoT, Code

• L-MBOP-E: Latent-Model Based Offline Planning with Extrinsic Policy Guided Exploration

  • Imran Adham, Hang Wang, Sen Lin, Junshan Zhang

  • IEEE International Conference on Mobility: Operations, Services, and Technologies (MOST) 2024

Multi-agent RL

• Ego-centric Learning of Communicative World Models for Autonomous Driving

  • Hang Wang, Dechen Gao, Qiaoyi Fang and Junshan Zhang

  • Preprint, 2025, Code

• Distributed Q-Learning with State Tracking for Multi-agent Networked Control

  • Video, Poster

  • Hang Wang, Sen Lin, Hamid Jafarkhani, Junshan Zhang

  • AAMAS 2021 (Extended Abstract)

Interdisciplinary Research

• Reinforcement Learning based Optical Material Composition Design

  • Paulina Escobar Diaz, Hang Wang, Junshan Zhang, Jeremy Munday

  • Ongoing Project

• Dual-layer Strengthened Collaborative Topic Regression Modeling for Predicting Drug Sensitivity

  • H. Wang, J. Xi, M. Wang, A. Li.

  • IEEE/ACM Transactions on Computational Biology and Bioinformatics(TCBB), 2018.

• One Inertial Sensor Based Metric for Upper-extremity Measurement

  • H. Wang, Mohamed Irfan Mohamed Refai, Bernhard J.F. van Beijnum

  • 12th International Joint Conference on Biomedical Engineering Systems and Technologies 2019, Prague, Czech Republic.

M.S. Thesis

• Reinforcement Learning based Control in Networked Systems

  • Qualifying Exam for Direct PhD student

B.E. Thesis

• Graphic Model Based Drug Sensitivity Prediction Research

  • Excellent Graduation Thesis Award, TOP 5%

US Patents

• Systems and Methods for Enhancing Motion Transformer Model with Diffusion Models through Knowledge Distillation

  • Hang Wang, Xin Ye, Feng Tao, Abhirup Mallik, Burhaneddin Yaman, Ren Liu

• Systems and Methods for World Model based Planning with Adaptive Finetuning for Autonomous Driving

  • Hang Wang, Xin Ye, Feng Tao, Chenbin Pan, Abhirup Mallik, Burhaneddin Yaman, Ren Liu

• World model based distributed learning for AI Agents

  • Junshan Zhang, Hang Wang and Dechen Gao

Professional Service

• Reviewer of ICML, NeurIPS, ICLR, AAAI, AISTAT, Inforcom, CIKM

• Reviewer of IEEE/ACM Transactions on Computational Biology and Bioinformatics

• Reviewer of IEEE Journal of Biomedical and Health Informatics

• Reviewer of IEEE Transactions on Signal Processing

• Reviewer of IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

• Reviewer of BMC Bioinformatics

• Tech Consultant for IntuitionLabs, San Jose, CA

Miscellaneous

• I've been wielding a violin bow since I was 7, though my neighbors might tell you I took a rather enthusiastic “pandemic revival” of my musical pursuits in 2020!

• When I'm not training AI models or debugging code, you'll find me advocating for academic workers’ rights as an active union member

• I proudly served as USTC union director back in college

• And hey, I also go by Mike (I picked it myself in kindergarten)!