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
Journal ArticleDOI
Computing Large Market Equilibria Using Abstractions
TL;DR: Two abstraction methods of interest for practitioners are introduced: filling in unknown valuations using techniques from matrix completion and reducing the problem size by aggregating groups of buyers/ items into smaller numbers of representative buyers/items and solving for equilibrium in this coarsened market.
Posted Content
Robust Multi-agent Counterfactual Prediction
TL;DR: The robustness of counterfactual claims for classic environments in market design: auctions, school choice, and social choice is investigated, and it is shown RMAC can be used in regimes where point identification is impossible (e.g. those which have multiple equilibria or non-injective maps from type distributions to outcomes).
Journal ArticleDOI
Efficient Heterogeneous Treatment Effect Estimation With Multiple Experiments and Multiple Outcomes
TL;DR: It is shown that even if an analyst cares only about the HTEs in one experiment for one metric, precision can be improved greatly by analyzing all of the data together to take advantage of cross-experiment and cross-outcome metric correlations.
Journal ArticleDOI
A note on proper scoring rules and risk aversion
TL;DR: This article showed that elicited probabilities are used as inputs to decision-making, and naive elicitors may violate first-order stochastic dominance when presented with risk neutral proper scoring rules.
Posted Content
Learning Existing Social Conventions in Markov Games
TL;DR: It is observed 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 convention, even in an environment where standard training methods very rarely find the true convention of the agent's partners.