Policy Abstraction and Nash Refinement in Tree-Exploiting PSRO

C Konicki, M Chakraborty, and MP Wellman 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2025. Forthcoming. Abstract Policy Space Response Oracles (PSRO) interleaves empirical game-theoretic analysis…
, , , , , , , ,

SRG paper wins Best Paper Award at ICAIF 2024

The paper titled "The Effect of Liquidity on the Spoofability of Financial Markets," led by Anri Gu, an undergraduate researcher with SRG, and coauthored by our recent PhD alum Yongzhao Wang, current PhD student Chris Mascioli, assistant research…

Market Making with Learned Beta Policies

Y Wang, R Savani, A Gu, C Mascioli, T Turocy, and MP Wellman 5th ACM International Conference on AI in Finance (ICAIF), pages 643-651, November 2024. Abstract In market making, a market maker (MM) can concurrently place many buy and sell…
, , , , , ,

Christine Konicki defends dissertation

On 21 October 2024, Christine Konicki successfully defended her PhD dissertation titled, "Exploiting Tree Structure in Empirical Game-Theoretic Analysis for Extensive-Form Games." Thanks to the dissertation committee members: Michael…

A Financial Market Simulation Environment for Trading Agents Using Deep Reinforcement Learning

C Mascioli, A Gu, Y Wang, M Chakraborty, and MP Wellman 5th ACM International Conference on AI in Finance (ICAIF), pages 117-125, November 2024. Abstract We present PyMarketSim, a financial market simulation environment designed for training…

The Effect of Liquidity on the Spoofability of Financial Markets

A Gu, Y Wang, C Mascioli, R Savani, T Turocy, M Chakraborty, and MP Wellman 5th ACM International Conference on AI in Finance (ICAIF), pages 239-247, November 2024. Recipient of the ICAIF24 Best Paper Award. Abstract We investigate the…
, , , ,

SRG paper wins Best Paper Award at ALA 2024 workshop

The paper titled "A Meta-Game Evaluation Framework for Deep Multiagent Reinforcement Learning," authored by Zun Li, while he was a PhD student with SRG, and Michael Wellman just won the best paper award at the 16th Adaptive and Learning Agents…

A Meta-Game Evaluation Framework for Deep Multiagent Reinforcement Learning

Z Li and MP Wellman 33rd International Joint Conference on Artificial Intelligence (IJCAI), pages 148-156, August 2024. earlier version won Best Paper Award at 16th Adaptive and Learning Agents (ALA) Workshop at AAMAS, May 2024. Abstract Evaluating…

Co-Learning Empirical Games and World Models

MO Smith and MP Wellman 1st Reinforcement Learning Conference (RLC), August 2024. Reinforcement Learning Journal, vol. 1, 2024, pp. 1-15. Abstract Game-based decision-making involves reasoning over both world dynamics and strategic interactions…

Empirical Game-Theoretic Analysis: A Survey

MP Wellman, K Tuyls, A Greenwald Accepted to Journal of Artificial Intelligence Research (JAIR), June 2024. To appear. Abstract In the empirical approach to game-theoretic analysis (EGTA), the model of the game comes not from declarative…