I am a senior research scientist at Facebook Artificial Intelligence research. My work includes both basic and applied research at the intersection of behavioral science, economics, game theory, and artificial intelligence. I hold a PhD in Behavioral Economics from Harvard.
My recent research involves exporting insights from behavioral economics and mechanism design to the design of smart artificial agents. I am also interested in trade going the other way: constructing new machine learning tools to improve the way we do behavioral/social science and market design. See my publication list (below) for more details.
At Facebook I have worked on many machine learning/data science projects including detecting clickbait, building large scale embedding systems, implementing advanced experimentation techniques, understanding network effects, and improving the way we measure hard to measure outcomes. Changes to Facebook resulting from some of these projects have been significant enough to appear in the popular press (Slate, NYT, Forbes). See my professional resume for more details.
I was once profiled in Pacific Standard. The article makes me seem much more interesting than I am.
I also like photography (mostly film). Check out my : alexpeys
"Maintaining cooperation in complex social dilemmas using deep reinforcement learning" (with Adam Lerer)
"Improving pairwise comparison models using Empirical Bayes" (with Stephen Ragain, Johan Ugander)
"Paying (for) Attention: The Impact of Information Processing Costs on Bayesian Inference" (with Xiaosheng Mu, Scott Kominers)
"In-Group favoritism caused by Pokemon Go and the use of machine learning for principled investigation of potential moderators" (with David Rand)
"Robust Multi-agent Counterfactual Prediction" (with Christian Kroer, Adam Lerer)
[NeurIPS 2019] [pdf]
"Fair Division Without Disparate Impact" (with Christian Kroer)
[Mechanism Design for Social Good] [pdf]
"Detecting heterogeneous treatment effects by combining observational and experimental data" (with Akos Lada, Diego Aparicio, Michael Bailey)
[EC2019] [old version]
"Computing large market equilibria using abstractions" (with Christian Kroer, Eric Sodomka, Nico Stier)
"PyTorch-BigGraph: A Large-scale Graph Embedding System" (with Adam Lerer, Jiajun Shen, Luca Wehrstedt, Abhijit Bose)
"Discovering Context Effects from Raw Choice Data" (with Arjun Seshadri, Johan Ugander)
"Learning Existing Social Conventions Using Observationally Augmented Self-play" (with Adam Lerer)
[AAAI-AIES2019-Best Paper] [pdf]
"Reinforcement Learning and Inverse Reinforcement Learning, with System 1 and System 2"
"Backplay: 'Man Muss Immer Umkeheren'" (with Cinjon Resnick, Roberta Raileanu, Sanyan Kapoor, Kyunghyun Cho, Joan Bruna)
[AAAI-RL in Games Workshop] [pdf]
"Prosocial learning agents solve generalized Stag Hunts better than selfish ones" (with Adam Lerer)
"Consequentialist conditional cooperation in social dilemmas with imperfect information" (with Adam Lerer)
"Learning causal effects from many randomized experiments using regularized instrumental variables" (with Dean Eckles)
"Towards AI that can solve social dilemmas" (with Adam Lerer)
[AAAI2018 Spring Symposium Series] [Proceedings]
Multi-Agent Cooperation and the Emergence of (Natural) Language" (with Angeliki Lazaridou and Marco Baroni)
"Using methods from machine learning to evaluate models of human choice under uncertainty" (with Jeff Naecker)
[Journal of Economic Behavior and Organization] [pdf]
"The Good, the Bad, and the Unflinchingly Selfish: Cooperative Decision-Making Can Be Predicted with High Accuracy Using Only Three Behavioral Types" (with Ziv Epstein and Dave Rand)
"Recency, Records and Recaps: Learning and Non-equilibrium Behavior in a Simple Decision Problem" (with Drew Fudenberg)
[EC2014, Transactions on Economics and Computation 2016] [pdf]
"When Punishment Doesn't Pay: 'Cold Glow' and Decisions to Punish" (with Aurelie Ouss)
[Journal of Law and Economics] [pdf]
"Why We Cooperate" (with Jillian Jordan and David Rand)
[Chapter in “The Moral Brain: Multidisciplinary Perspectives”] [pdf]
"Social Heuristics Shape Intuitive Cooperation" (with David Rand, Gordon Kraft-Todd, George Newman, Owen Wurzbacher, Martin Nowak and Joshua Greene)
[Nature Comms] [pdf] [Journal Version] [Data and Code]
Website powered by w3.css