Austin Nguyen defends dissertation proposal
On March 30, 2026, Austin Nguyen presented and successfully defended his dissertation proposal titled "Offline Learning Paradigms in Game-Theoretic Multiagent Reinforcement Learning."
The dissertation committee comprises:
Michael Wellman…
Madelyn Gatchel defends dissertation proposal
On April 14, 2025, Madelyn Gatchel presented and successfully defended her dissertation proposal titled "Learning and Reasoning About Parameterized Families of Games."
The dissertation committee comprises:
Michael Wellman [chair]
Elizabeth…
Learning Bayesian Game Families, with Application to Mechanism Design
M Gatchel and MP Wellman
25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2026. To appear.
Abstract
Learning or estimating game models from data typically entails inducing separate models for each setting,…
Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning
A Nguyen, and MP Wellman
25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2026. To appear.
Abstract
Offline learning of strategies takes data efficiency to its extreme by restricting algorithms to a…
SRG team is a winner in the AgentX-AgentBeats Competition
Our team MAizeBargAIn, led by PhD students Gabriel Smithline and Chris Mascioli, won 1st place in the Multiagent Evaluation category in Phase 1 of the AgentX-AgentBeats Competition, hosted by Berkeley RDI in conjunction with the Agentic AI…
Prof. Wellman receives 2026 IFAAMAS Influential Paper Award
Prof. Wellman has been selected as a recipient of the 2026 IFAAMAS Influential Paper Award to be presented at the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) for the 2003 paper "Nash Q-learning for…
Madelyn Gatchel finishes as runner-up at CSE Graduate Honors Competition
Madelyn Gatchel finished as runner-up at the 22nd Annual CSE Graduate Honors Competition held on Nov 10, 2025, where she delivered a 15 min presentation on her research topic "Learning and Reasoning about Parameterized Families of Games."…
Market Selection with Midpoint Matching: A Strategic Agent-Based Analysis
G Smithline, A Gu, and MP Wellman
6th ACM International Conference on AI in Finance (ICAIF), November 2025. To appear.
Abstract
We study midpoint matching through Nasdaq’s Midpoint Extended-Life Order (M-ELO) mechanism, which offers non-displayed…
Gabe Smithline Passes Prelim
PhD student Gabe Smithline passed the CSE prelim exam, based on his directed study project titled “Measuring Competition and Cooperation in LLM Bargaining: An Empirical Meta-Game Analysis.”
Congratulations, Gabe!
