A
Alexander Peysakhovich
Researcher at Facebook
Publications - 80
Citations - 4072
Alexander Peysakhovich is an academic researcher from Facebook. The author has contributed to research in topics: Reinforcement learning & Behavioral economics. The author has an hindex of 21, co-authored 75 publications receiving 3285 citations. Previous affiliations of Alexander Peysakhovich include Yale University & Harvard University.
Papers
More filters
Posted Content
Learning Existing Social Conventions via Observationally Augmented Self-Play
TL;DR: In this article, the authors consider the problem of an agent learning a policy for a coordination game in a simulated environment and then using this policy when it enters an existing group and show that augmenting MARL with a small amount of imitation learning greatly increases the probability that the strategy found by MARL fits well with the existing social conventions.
Proceedings ArticleDOI
Computing Large Market Equilibria using Abstractions
TL;DR: This work shows how to bound important quantities such as regret, envy, Nash social welfare, Pareto optimality, and maximin share when the abstracted prices and allocations are used in place of the real equilibrium.
Posted Content
Recency, Records and Recaps: Learning and Non-Equilibrium Behavior in a Simple Decision Problem
TL;DR: The authors show that learning models that heavily discount past information (i.e. display recency bias) explain patterns of behavior better than Nash, cursed equilibrium, or behavioral equilibrium, while providing counterfactual information or a record of past outcomes does little to aid convergence to optimal strategies.
Posted Content
Learning Social Conventions in Markov Games.
TL;DR: It is shown that adding a small amount of imitation learning during self-play training greatly increases the probability that the strategy found by self- play fits well with the social convention the agent will face at test time, even in an environment where standard independent multi-agent RL very rarely finds the correct test-time equilibrium.
Journal ArticleDOI
The Good, the Bad, and the Unflinchingly Selfish: Cooperative Decision-Making Can Be Predicted with High Accuracy Using Only Three Behavioral Types
TL;DR: Evidence is provided that this inclination to cooperate cannot be well proxied by other personality/morality survey measures or demographics, and thus is a natural kind (or "cooperative phenotype").