Search Results for author:
Found 20 papers, 3 papers with code
“Other-Play” for Zero-Shot Coordination
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)
Attention Sorting Combats Recency Bias In Long Context Language Models
Current language models often fail to incorporate long contexts efficiently during generation.
Diagnosis Uncertain Models For Medical Risk Prediction
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.
Pseudo-Euclidean Attract-Repel Embeddings for Undirected Graphs
Dot product embeddings take a graph and construct vectors for nodes such that dot products between two vectors give the strength of the edge.
Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions
We apply our methods to study teams of artificial RL agents as well as real world teams from professional sports.
Fair Division Without Disparate Impact
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.
Backplay: 'Man muss immer umkehren'
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.
Robust Multi-agent Counterfactual Prediction
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.
Discovering Context Effects from Raw Choice Data
An important class of such contexts is the composition of the choice set.
Computing large market equilibria using abstractions
Computing market equilibria is an important practical problem for market design, for example in fair division of items.
Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2
Under the rational actor assumption techniques such as inverse reinforcement learning (IRL) can be used to infer a person's goals from their actions.
Improving pairwise comparison models using Empirical Bayes shrinkage
As such, different models of the comparison process lead to different shrinkage estimators.
Backplay: "Man muss immer umkehren"
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.
Learning Existing Social Conventions via Observationally Augmented Self-Play
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.
Consequentialist conditional cooperation in social dilemmas with imperfect information
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.
Prosocial learning agents solve generalized Stag Hunts better than selfish ones
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
Maintaining cooperation in complex social dilemmas using deep reinforcement learning
Social dilemmas are situations where individuals face a temptation to increase their payoffs at a cost to total welfare.
Learning causal effects from many randomized experiments using regularized instrumental variables
Scientific and business practices are increasingly resulting in large collections of randomized experiments.
Multi-Agent Cooperation and the Emergence of (Natural) Language
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.
Combining observational and experimental data to find heterogeneous treatment effects
However traditional A/B tests are often underpowered to identify these heterogeneous effects.
