, ,

Max finishes as finalist at CSE Graduate Honors Competition

Max Smith was one of the five finalists at the 18th Annual CSE Graduate Honors Competition held virtually on Nov 10, 2021, where he delivered a short presentation on his research titled "Strategic Knowledge Transfer." He was selected as the…

Building Action Sets in a Deep Reinforcement Learner

Y Wang, A Sinha, S CH-Wang, and MP Wellman 20th IEEE International Conference on Machine Learning and Applications (ICMLA-21), pages 484–489, December 2021. Abstract In many policy-learning applications, the agent may execute a set of actions…

Evolution Strategies for Approximate Solution of Bayesian Games

Z Li and MP Wellman 35th AAAI Conference on Artificial Intelligence, pages 5531-5540, Feb 2021. Abstract We address the problem of solving complex Bayesian games, characterized by high-dimensional type and action spaces, many (> 2) players,…

Iterative Empirical Game Solving via Single Policy Best Response

MO Smith, T Anthony, and MP Wellman 9th International Conference on Learning Representations (ICLR), Spotlight Presentation, May 2021. Abstract Policy-Space Response Oracles (PSRO) is a general algorithmic framework for learning policies…

Structure learning for approximate solution of many-player games

Z Li and MP Wellman 34th AAAI Conference on Artificial Intelligence, pages 2119-2127, Feb 2020. Abstract Games with many players are difficult to solve or even specify without adopting structural assumptions that enable representation in…