Joseph Campbell
Assistant Professor of Computer Science
Joseph Campbell is an Assistant Professor in the Department of Computer Science at Purdue University, where he leads the Collaborative AI for Machines and People (CAMP) Lab. His research bridges machine learning and robotics, with a particular focus on explainable machine learning. Joseph is especially interested in how agents can leverage explanations not just for transparency but for enhancing their own capabilities through self-improvement, particularly… ↓More
Joined department: Fall 2024
Research Areas
- Robotics and Computer Vision
- Artificial Intelligence, Machine Learning, and Natural Language Processing
Education
Ph.D., Arizona State University, Computer Science (2021)
M.S., Arizona State University, Computer Engineering (2016)
B.S., Arizona State University, Computer Science (2010)
Joseph Campbell is an Assistant Professor in the Department of Computer Science at Purdue University, where he leads the Collaborative AI for Machines and People (CAMP) Lab. His research bridges machine learning and robotics, with a particular focus on explainable machine learning. Joseph is especially interested in how agents can leverage explanations not just for transparency but for enhancing their own capabilities through self-improvement, particularly in lifelong learning settings. This includes model-level explanations which facilitate agent introspection, e.g. concept-based explanations, and behavior-level explanations which facilitate better decision-making by modeling other agents, e.g. theory of mind.
Joseph earned his Ph.D., M.S., and B.S. degrees in Computer Science and Computer Engineering from Arizona State University. Before transitioning to academia, he spent more than five years in industry as a software engineer, gaining practical experience that informs his research. Prior to joining Purdue, he was a Postdoctoral Fellow in the Robotics Institute at Carnegie Mellon University.
Selected Publications
Muhan Lin, Shuyang Shi, Yue Guo, Behdad Chalaki, Vaishnav Tadiparthi, Ehsan Moradi Pari, Simon Stepputtis, Joseph Campbell, and Katia Sycara. Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models. Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings, 2024.
Huao Li, Yu Quan Chong, Simon Stepputtis, Joseph Campbell, Dana Hughes, Michael Lewis, and Katia Sycara. Theory of Mind for Multi-Agent Collaboration via Large Language Models. Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
Joseph Campbell, Yue Guo, Fiona Xie, Simon Stepputtis, and Katia Sycara. Introspective Action Advising for Interpretable Transfer Learning. Conference on Lifelong Learning Agents (CoLLAs), 2023.
Yuzhe Lu, Yilong Qin, Runtian Zhai, Andrew Shen, Ketong Chen, Zhenlin Wang, Soheil Kolouri, Simon Stepputtis, Joseph Campbell, and Katia Sycara. Characterizing Out-of-Distribution Error via Optimal Transport. Conference on Neural Information Processing Systems (NeurIPS), 2023.
Renos Zabounidis*, Joseph Campbell*, Simon Stepputtis, Dana Hughes, and Katia Sycara. Concept Learning for Interpretable Multi-Agent Reinforcement Learning. Conference on Robot Learning (CoRL), 2022.