238 citations · 404 across the 17 of their papers we have counts for
21 papers
Language Agents as Digital Representatives in Collective Decision-Making
Daniel Jarrett, Miruna Pîslar, Michiel A. Bakker +6
Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context,…
Using deep reinforcement learning to promote sustainable human behaviour on a common pool resource problem
Raphael Koster, Miruna Pîslar, Andrea Tacchetti +7
A canonical social dilemma arises when finite resources are allocated to a group of people, who can choose to either reciprocate with interest, or keep the proceeds for themselves.…
Gemma: Open Models Based on Gemini Research and Technology
Gemma Team, Thomas Mesnard, Cassidy Hardin +105
This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate stro…
Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience
Manfred Diaz, Liam Paull, Andrea Tacchetti
Teacher-Student Curriculum Learning (TSCL) is a curriculum learning framework that draws inspiration from human cultural transmission and learning. It involves a teacher algorithm…
Scaling Opponent Shaping to High Dimensional Games
Akbir Khan, Timon Willi, Newton Kwan +5
In multi-agent settings with mixed incentives, methods developed for zero-sum games have been shown to lead to detrimental outcomes. To address this issue, opponent shaping (OS) me…
Unifying Grokking and Double Descent
Xander Davies, Lauro Langosco, David Krueger
A principled understanding of generalization in deep learning may require unifying disparate observations under a single conceptual framework. Previous work has studied \emph{grokk…
Generative Adversarial Equilibrium Solvers
Denizalp Goktas, David C. Parkes, Ian Gemp +5
We introduce the use of generative adversarial learning to compute equilibria in general game-theoretic settings, specifically the generalized Nash equilibrium (GNE) in pseudo-game…
Leave Graphs Alone: Addressing Over-Squashing without Rewiring
Domenico Tortorella, Alessio Micheli
Recent works have investigated the role of graph bottlenecks in preventing long-range information propagation in message-passing graph neural networks, causing the so-called `over-…
Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers
Luke Marris, Ian Gemp, Thomas Anthony +3
Solution concepts such as Nash Equilibria, Correlated Equilibria, and Coarse Correlated Equilibria are useful components for many multiagent machine learning algorithms. Unfortunat…
Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments
Ian Gemp, Thomas Anthony, Yoram Bachrach +24
The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simul…
The Good Shepherd: An Oracle Agent for Mechanism Design
Jan Balaguer, Raphael Koster, Christopher Summerfield +1
From social networks to traffic routing, artificial learning agents are playing a central role in modern institutions. We must therefore understand how to leverage these systems to…
HCMD-zero: Learning Value Aligned Mechanisms from Data
Jan Balaguer, Raphael Koster, Ari Weinstein +4
Artificial learning agents are mediating a larger and larger number of interactions among humans, firms, and organizations, and the intersection between mechanism design and machin…
Human-centered mechanism design with Democratic AI
Raphael Koster, Jan Balaguer, Andrea Tacchetti +8
Building artificial intelligence (AI) that aligns with human values is an unsolved problem. Here, we developed a human-in-the-loop research pipeline called Democratic AI, in which…
Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descent
Ian Gemp, Rahul Savani, Marc Lanctot +6
Nash equilibrium is a central concept in game theory. Several Nash solvers exist, yet none scale to normal-form games with many actions and many players, especially those with payo…
D3C: Reducing the Price of Anarchy in Multi-Agent Learning
Ian Gemp, Kevin R. McKee, Richard Everett +4
In multiagent systems, the complex interaction of fixed incentives can lead agents to outcomes that are poor (inefficient) not only for the group, but also for each individual. Pri…
Learning to Play No-Press Diplomacy with Best Response Policy Iteration
Thomas Anthony, Tom Eccles, Andrea Tacchetti +11
Recent advances in deep reinforcement learning (RL) have led to considerable progress in many 2-player zero-sum games, such as Go, Poker and Starcraft. The purely adversarial natur…
Should I tear down this wall? Optimizing social metrics by evaluating novel actions
János Kramár, Neil Rabinowitz, Tom Eccles +1
One of the fundamental challenges of governance is deciding when and how to intervene in multi-agent systems in order to impact group-wide metrics of success. This is particularly…
Learning Truthful, Efficient, and Welfare Maximizing Auction Rules
Andrea Tacchetti, DJ Strouse, Marta Garnelo +2
From social networks to supply chains, more and more aspects of how humans, firms and organizations interact is mediated by artificial learning agents. As the influence of machine…
Relational Forward Models for Multi-Agent Learning
Andrea Tacchetti, H. Francis Song, Pedro A. M. Mediano +5
The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to…
Relational inductive biases, deep learning, and graph networks
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst +24
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, i…
Visual Interaction Networks
Nicholas Watters, Andrea Tacchetti, Theophane Weber +3
From just a glance, humans can make rich predictions about the future state of a wide range of physical systems. On the other hand, modern approaches from engineering, robotics, an…