Research Projects
My current research focuses on market entry strategy and performance guarantees for decentralized control systems.
Market Entry Strategy
We apply existing reinforcement learning (RL) techniques to the domain of market entry and exit strategy. We show that in a simple economic game, RL-based agents outperform rule-based agents in their ability to maximize capital subject to market entry and exit decisions. Our initial results serve as proof of concept that modern artificial intelligence can uncover novel insights in the field of microeconomic strategy.
Decentralized Control Systems
How do the performance guarantees of decentralized control systems degrade due to the selfish behavior of individual agents? It has been shown [1] that under certain conditions, we can guarantee that any Nash equilibrium of the game attains at least 1/2 the welfare arising from socially optimal play. We seek to find classes of games that improve on this 1/2 guarantee.
[1] A. Vetta, "Nash equilibria in competitive societies, with applications to facility location, traffic routing and auctions," The 43rd Annual IEEE Symposium on Foundations of Computer Science, 2002. Proceedings., Vancouver, BC, Canada, 2002, pp. 416-425