Alexander Peysakhovich

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 41

Top Topics

Reinforcement Learning

Imperfect Information

Pairwise Comparison

Top Venues

Publications

William Berman, Alexander Peysakhovich
MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data. CoRR (2024)
Alexander Peysakhovich, Adam Lerer
Attention Sorting Combats Recency Bias In Long Context Language Models. CoRR (2023)
Alexander Peysakhovich, Christian Kroer, Nicolas Usunier
Implementing Fairness Constraints in Markets Using Taxes and Subsidies. FAccT (2023)
Alexander Peysakhovich, Rich Caruana, Yin Aphinyanaphongs
Diagnosis Uncertain Models For Medical Risk Prediction. CoRR (2023)
Christian Kroer, Alexander Peysakhovich, Eric Sodomka, Nicolás E. Stier Moses
Computing Large Market Equilibria Using Abstractions. Oper. Res. 70 (1) (2022)
Alexander Peysakhovich, Christian Kroer, Nicolas Usunier
Parity in Markets - Methods, Costs, and Consequences. CoRR (2022)
Alexander Peysakhovich, Léon Bottou
An Attract-Repel Decomposition of Undirected Networks. CoRR (2021)
Tom Yan, Christian Kroer, Alexander Peysakhovich
Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions. NeurIPS (2020)
Tom Yan, Christian Kroer, Alexander Peysakhovich
Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions. CoRR (2020)
Jack Parker-Holder, Luke Metz, Cinjon Resnick, Hengyuan Hu, Adam Lerer, Alistair Letcher, Alexander Peysakhovich, Aldo Pacchiano, Jakob N. Foerster
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian. NeurIPS (2020)
Christian Kroer, Alexander Peysakhovich
Scalable Fair Division for 'At Most One' Preferences. CoRR (2019)
Adam Lerer, Alexander Peysakhovich
Learning Existing Social Conventions via Observationally Augmented Self-Play. AIES (2019)
Alexander Peysakhovich
Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2. AIES (2019)
Alexander Peysakhovich, Christian Kroer
Fair Division Without Disparate Impact. CoRR (2019)
Arjun Seshadri, Alexander Peysakhovich, Johan Ugander
Discovering Context Effects from Raw Choice Data. CoRR (2019)
Ziv Epstein, Alexander Peysakhovich, David G. Rand
The Good, the Bad, and the Unflinchingly Selfish: Pro-sociality can be Well Predicted Using Payoffs and Three Behavioral Types. ACM Trans. Economics and Comput. 7 (3) (2019)
Christian Kroer, Alexander Peysakhovich, Eric Sodomka, Nicolás E. Stier Moses
Computing Large Market Equilibria using Abstractions. EC (2019)
Alexander Peysakhovich, Christian Kroer, Adam Lerer
Robust Multi-agent Counterfactual Prediction. NeurIPS (2019)
Christian Kroer, Alexander Peysakhovich, Eric Sodomka, Nicolás E. Stier Moses
Computing large market equilibria using abstractions. CoRR (2019)
Alexander Peysakhovich, Christian Kroer, Adam Lerer
Robust Multi-agent Counterfactual Prediction. CoRR (2019)
Akos Lada, Alexander Peysakhovich, Diego Aparicio, Michael Bailey
Observational Data for Heterogeneous Treatment Effects with Application to Recommender Systems. EC (2019)
Adam Lerer, Ledell Wu, Jiajun Shen, Timothée Lacroix, Luca Wehrstedt, Abhijit Bose, Alexander Peysakhovich
PyTorch-BigGraph: A Large-scale Graph Embedding System. CoRR (2019)
Alexander Peysakhovich, Adam Lerer
Prosocial Learning Agents Solve Generalized Stag Hunts Better than Selfish Ones. AAMAS (2018)
Alexander Peysakhovich
Reinforcement learning and inverse reinforcement learning with system 1 and system 2. CoRR (2018)
Alexander Peysakhovich, Adam Lerer
Consequentialist Conditional Cooperation in Social Dilemmas with Imperfect Information (Short Workshop Version). AAAI Workshops (2018)
Adam Lerer, Alexander Peysakhovich
Learning Social Conventions in Markov Games. CoRR (2018)
Stephen Ragain, Alexander Peysakhovich, Johan Ugander
Improving pairwise comparison models using Empirical Bayes shrinkage. CoRR (2018)
Alexander Peysakhovich, Adam Lerer
Towards AI that Can Solve Social Dilemmas. AAAI Spring Symposia (2018)
Alexander Peysakhovich, Dean Eckles
Learning Causal Effects From Many Randomized Experiments Using Regularized Instrumental Variables. WWW (2018)
Alexander Peysakhovich, Adam Lerer
Consequentialist conditional cooperation in social dilemmas with imperfect information. ICLR (Poster) (2018)
Angeliki Lazaridou, Alexander Peysakhovich, Marco Baroni
Multi-Agent Cooperation and the Emergence of (Natural) Language. ICLR (2017)
Adam Lerer, Alexander Peysakhovich
Maintaining cooperation in complex social dilemmas using deep reinforcement learning. CoRR (2017)
Alexander Peysakhovich, Adam Lerer
Prosocial learning agents solve generalized Stag Hunts better than selfish ones. CoRR (2017)
Alexander Peysakhovich, Adam Lerer
Consequentialist conditional cooperation in social dilemmas with imperfect information. CoRR (2017)
Alexander Peysakhovich, Johan Ugander
Learning context-dependent preferences from raw data. NetEcon@EC (2017)
Angeliki Lazaridou, Alexander Peysakhovich, Marco Baroni
Multi-Agent Cooperation and the Emergence of (Natural) Language. CoRR (2016)
Alexander Peysakhovich, Akos Lada
Combining observational and experimental data to find heterogeneous treatment effects. CoRR (2016)
Ziv Epstein, Alexander Peysakhovich, David G. Rand
The Good, the Bad, and the Unflinchingly Selfish: Cooperative Decision-Making can be Predicted with high Accuracy when using only Three Behavioral Types. EC (2016)
Alexander Peysakhovich, Uma R. Karmarkar
Asymmetric Effects of Favorable and Unfavorable Information on Decision Making Under Ambiguity. Manag. Sci. 62 (8) (2016)
Drew Fudenberg, Alexander Peysakhovich
Recency, Records, and Recaps: Learning and Nonequilibrium Behavior in a Simple Decision Problem. ACM Trans. Economics and Comput. 4 (4) (2016)
Alexander Peysakhovich, David G. Rand
Habits of Virtue: Creating Norms of Cooperation and Defection in the Laboratory. Manag. Sci. 62 (3) (2016)
Drew Fudenberg, Alexander Peysakhovich
Recency, records and recaps: learning and non-equilibrium behavior in a simple decision problem. EC (2014)