I am a postdoctoral researcher at the Autonomous Agents and Distributed Intelligence Lab with Dr. Kagan Tumer in the AI-Caring Institute. I completed my PhD in Robotics and AI at Oregon State University, where I developed learning and diversity-search techniques for cooperative multi-agent settings.
My research is at the intersection of reinforcement learning, evolutionary algorithms, game theory, and ethics. Broadly, I am interested in developing methods that allow asymmetric agents — agents with distinct capabilities and objectives — to cooperate and work in teams with diverse partners.
At the AI-Caring Institute, my work synthesizes multi-objective solution concepts that facilitate collective reasoning required to pursue high-level, long-term, dynamic, and potentially conflicting objectives such as an older adult’s independence and safety. This induces three distinct challenges: 1) Identifying the representative set of care coordination tasks, such as collaborative cleaning and health monitoring, that encapsulate the diverse responsibilities and interactions necessary for providing comprehensive care in a healthcare setting; 2) Inferring the core characteristics of the tasks such as the required agent capabilities, the associated objectives, tasks priorities and interdependence, and the expected cooperative outcomes to ensure wellbeing; and 3) Developing a coverage set of diverse trade-offs that account for the collective considerations of caregivers, healthcare provides and embodied agents.
selected publications
-
Objective-Informed Diversity for Multi-Objective Multiagent Coordination
In the European Conference on Artificial Intelligence (ECAI). 2024.
[ pdf ] -
Informed Diversity Search for Learning in Asymmetric Multiagent Systems
In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO). 2024.
[ pdf ] -
Learning Synergies for Multi-Objective Optimization in Asymmetric Multiagent Systems
In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO). 2023.
[ pdf ] -
Learning Inter-Agent Synergies in Asymmetric Multiagent Systems
Proceedings of the 22nd International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). 2023.
[ pdf ] -
Diversifying behaviors for learning in Asymmetric Multiagent Systems
In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO). 2022.
[ pdf ] -
Balancing Teams with Quality-Diversity for Heterogeneous Multiagent Coordination
In International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). 2022.
[ pdf ] -
Gaussian Processes as Multiagent Reward Models
Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). 2020.
[ pdf ] -
Dirichlet-Multinomial Counterfactual Rewards for Heterogeneous Multiagent Systems
In 2019 International Symposium on Multi-Robot and Multi-Agent Systems (MRS), IEEE. 2019.
[ pdf ]