no code implementations • ICML 2020 • Hengyuan Hu, Alexander Peysakhovich, Adam Lerer, Jakob Foerster
We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e. g. humans).
Multi-agent Reinforcement Learning Reinforcement Learning (RL)
no code implementations • 28 Sep 2023 • Alexander Peysakhovich, Adam Lerer
Current language models often fail to incorporate long contexts efficiently during generation.
no code implementations • 29 Jun 2023 • Alexander Peysakhovich, Rich Caruana, Yin Aphinyanaphongs
We consider a patient risk models which has access to patient features such as vital signs, lab values, and prior history but does not have access to a patient's diagnosis.
no code implementations • 17 Jun 2021 • Alexander Peysakhovich, Anna Klimovskaia Susmel, Leon Bottou
Dot product embeddings take a graph and construct vectors for nodes such that dot products between two vectors give the strength of the edge.
no code implementations • NeurIPS 2020 • Tom Yan, Christian Kroer, Alexander Peysakhovich
We apply our methods to study teams of artificial RL agents as well as real world teams from professional sports.
no code implementations • 6 Jun 2019 • Alexander Peysakhovich, Christian Kroer
We consider the problem of dividing items between individuals in a way that is fair both in the sense of distributional fairness and in the sense of not having disparate impact across protected classes.
no code implementations • ICLR 2019 • Cinjon Resnick, Roberta Raileanu, Sanyam Kapoor, Alexander Peysakhovich, Kyunghyun Cho, Joan Bruna
Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency.
no code implementations • NeurIPS 2019 • Alexander Peysakhovich, Christian Kroer, Adam Lerer
We consider the problem of using logged data to make predictions about what would happen if we changed the `rules of the game' in a multi-agent system.
no code implementations • 8 Feb 2019 • Arjun Seshadri, Alexander Peysakhovich, Johan Ugander
An important class of such contexts is the composition of the choice set.
no code implementations • 18 Jan 2019 • Christian Kroer, Alexander Peysakhovich, Eric Sodomka, Nicolas E. Stier-Moses
Computing market equilibria is an important practical problem for market design, for example in fair division of items.
no code implementations • 19 Nov 2018 • Alexander Peysakhovich
Under the rational actor assumption techniques such as inverse reinforcement learning (IRL) can be used to infer a person's goals from their actions.
no code implementations • 24 Jul 2018 • Stephen Ragain, Alexander Peysakhovich, Johan Ugander
As such, different models of the comparison process lead to different shrinkage estimators.
1 code implementation • 18 Jul 2018 • Cinjon Resnick, Roberta Raileanu, Sanyam Kapoor, Alexander Peysakhovich, Kyunghyun Cho, Joan Bruna
Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency.
no code implementations • 26 Jun 2018 • Adam Lerer, Alexander Peysakhovich
When there are multiple possible conventions we show that learning a policy via multi-agent reinforcement learning (MARL) is likely to find policies which achieve high payoffs at training time but fail to coordinate with the real group into which the agent enters.
no code implementations • ICLR 2018 • Alexander Peysakhovich, Adam Lerer
We show how to construct such strategies using deep reinforcement learning techniques and demonstrate, both analytically and experimentally, that they are effective in social dilemmas beyond simple matrix games.
no code implementations • 8 Sep 2017 • Alexander Peysakhovich, Adam Lerer
We extend existing work on reward-shaping in multi-agent reinforcement learning and show that that making a single agent prosocial, that is, making them care about the rewards of their partners can increase the probability that groups converge to good outcomes.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • ICLR 2018 • Adam Lerer, Alexander Peysakhovich
Social dilemmas are situations where individuals face a temptation to increase their payoffs at a cost to total welfare.
no code implementations • 4 Jan 2017 • Alexander Peysakhovich, Dean Eckles
Scientific and business practices are increasingly resulting in large collections of randomized experiments.
1 code implementation • 21 Dec 2016 • Angeliki Lazaridou, Alexander Peysakhovich, Marco Baroni
The sender is told one of them is the target and is allowed to send a message from a fixed, arbitrary vocabulary to the receiver.
no code implementations • 8 Nov 2016 • Alexander Peysakhovich, Akos Lada
However traditional A/B tests are often underpowered to identify these heterogeneous effects.