avatar

Peihong Yu

Ph.D. Candidate
University of Maryland, College Park
peihong@umd.edu


About Me

I am a Ph.D. student in Computer Science at University of Maryland, College Park, working with Prof. Pratap Tokekar.

I currently work in the field of Reinforcement Learning, mostly Multi-Agent RL. The core of my work is to address the challenges of training efficiency and generalizability, allowing autonomous agents to learn effectively and perform robustly across diverse scenarios.

Prior to that, I was a master’s student in School of Information Science and Technology at ShanghaiTech University, co-supervised by Prof. Jingyi Yu and Prof. Laurent Kneip, working on SLAM and 3D Reconstruction.

Experiences

SRI Logo
SRI International
Research Scientist Intern
Summer 2023
Meta Logo
Meta Reality Lab
Research Scientist Intern
Summer 2022

Publications

  1. DC@AAMAS 2025
    Learning with Less Effort: Efficient Training and Generalization in (Multi-)Robot Systems
    Peihong Yu
    Doctoral Consortium @ AAMAS, 2025

  2. AAMAS 2025
    TACTIC: Task-Agnostic Contrastive pre-Training for Inter-Agent Communication
    Peihong Yu, Manav Mishra, Syed Zaidi, Pratap Tokekar
    The 24th International Conference on Autonomous Agents and Multi-Agent Systems, 2025
    PDF

  3. TMLR 2025
    Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning
    Peihong Yu, Manav Mishra, Alec Koppel, Carl Busart, Priya Narayan, Dinesh Manocha, Amrit Singh Bedi, Pratap Tokekar
    Transactions on Machine Learning Research, 2025
    PDF Code Project Page

  4. OOD@CORL 2023
    Enhancing Multi-Agent Coordination through Common Operating Picture Integration
    Peihong Yu, Bhoram Lee, Aswin Raghavan, Supun Samarasekara, Pratap Tokekar, James Zachary Hare
    Workshop on Out-of-Distribution Generalization in Robotics at CoRL, 2023
    PDF

  5. IEEE Access 2020
    Accurate Line-Based Relative Pose Estimation with Camera Matrices
    Peihong Yu, Cen Wang, Zhirui Wang, Jingyi Yu, Laurent Kneip
    IEEE Access, 2020
    PDF Video

  6. ICCV 2017
    Ray Space Features for Plenoptic Structure-from-Motion
    Yingliang Zhang, Peihong Yu, Wei Yang, Yuanxi Ma, Jingyi Yu
    IEEE International Conference on Computer Vision (ICCV), 2017
    PDF

  7. ICCP 2017
    The Light Field 3d Scanner
    Yingliang Zhang, Zhong Li, Wei Yang, Peihong Yu, Haiting Lin, Jingyi Yu
    IEEE International Conference on Computational Photography (ICCP), 2017
    PDF

Preprints

  1. Preprint
    Sketch-to-Skill: Bootstrapping Robot Learning with Human Drawn Trajectory Sketches
    Peihong Yu*, Amisha Bhaskar*, Anukriti Singh, Zahiruddin Mahammad, and Pratap Tokekar.
    PDF

  2. Preprint
    VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences
    Anukriti Singh, Amisha Bhaskar, Peihong Yu, Souradip Chakraborty, Ruthwik Dasyam, Amrit Bedi, Pratap Tokekar.
    PDF

  3. Preprint
    Towards Scalable General Utility Reinforcement Learning: Occupancy Approximation, Sample Complexity and Global Optimality
    Anas Barakat, Souradip Chakraborty, Peihong Yu, Pratap Tokekar, Amrit Singh Bedi.
    PDF

  4. Preprint
    Insta-RS: Instance-wise Randomized Smoothing for Improved Robustness and Accuracy
    Chen Chen, Kezhi Kong, Peihong Yu, Juan Luque, Tom Goldstein, Furong Huang.
    PDF

Services

Conference Reviewers

Journal Reviewers

Mentoring

Teaching Asistants

Mentoring


Powered by Jekyll and Minimal Light theme.