Mason Wright

Iterated Deep Reinforcement Learning in Games: History-Aware Training for Improved Stability

M Wright, Y Wang, and MP Wellman Proceedings of the 20th ACM Conference on Economics and Computation, pages 617-636, June 2019. Abstract Deep reinforcement learning (RL) is a powerful method for generating policies in complex environments,…
Mason Wright
, , ,

My interview with Bill Powers on AI Decision Makers

https://youtu.be/SnTf-iWUTpk Recorded June 2018, as part of a series on Machine Behavior, in conjunction with publication of a position paper in Nature on the topic.
Mason Wright

Machine Behaviour

I Rahwan, M Cebrian, N Obradovich, J Bongard, 18 others, and MP Wellman Nature, 568:477–486, 2019. Abstract Machines powered by artificial intelligence increasingly mediate our social, cultural, economic and political interactions. Understanding…
Mason Wright

Incentivizing Collaboration in a Competition

A Sinha and MP Wellman Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 556–564, May 2019. Abstract Research and design competitions aim to promote innovation or creative production,…
, , ,

Xintong Wang defends thesis proposal

(belated announcement) On 20 December 2018, Xintong Wang presented and successfully defended her thesis proposal: "Studies on the Computational Modeling and Design of Financial Markets". The dissertation committee comprises: Michael…
Mason Wright

Deception in Finitely Repeated Security Games

TH Nguyen, Y Wang, A Sinha, and MP Wellman 33rd AAAI Conference on Artificial Intelligence, Jan/Feb 2019. Abstract Allocating resources to defend targets from attack is often complicated by uncertainty about the attacker’s capabilities,…
Mason Wright
, , ,

Mason Wright defends thesis

Congratulations to Mason Wright, on a successful thesis defense. And a special thanks to Mason's thesis committee members: Grant Schoenebeck Demos Teneketzis Jenna Wiens
Mason Wright

A Learning and Masking Approach to Secure Learning

L Nguyen, S Wang, and A Sinha Ninth Conference on Decision and Game Theory for Security, October 2018. Abstract Deep Neural Networks (DNNs) have been shown to be vulnerable against adversarial examples, which are data points cleverly constructed…
Mason Wright

Stackelberg Security Games: Looking Beyond a Decade of Success

A Sinha, F Fang, B An, C Kiekintveld, and M Tambe 27th International Joint Conference on Artificial Intelligence, July 2018. Abstract The Stackelberg Security Game (SSG) model has been immensely influential in security research since it…
Mason Wright

Bounding regret in empirical games

S Jecmen, A Sinha, Z Li, L Tran-Thanh 34th AAAI Conference on Artificial Intelligence (AAAI), 2020. Abstract Empirical game-theoretic analysis refers to a set of models and techniques for solving large-scale games. However, there is a lack…