1
|
Gemp I, Anthony T, Bachrach Y, Bhoopchand A, Bullard K, Connor J, Dasagi V, De Vylder B, Duéñez-Guzmán E, Elie R, Everett R, Hennes D, Hughes E, Khan M, Lanctot M, Larson K, Lever G, Liu S, Marris L, McKee KR, Muller P, Pérolat J, Strub F, Tacchetti A, Tarassov E, Wang Z, Tuyls K. Developing, evaluating and scaling learning agents in multi-agent environments. AI COMMUN 2022. [DOI: 10.3233/aic-220113] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
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 simulating social dilemmas in rich spatial environments and training 3-d humanoids in difficult team coordination tasks. A signature aim of our group is to use the resources and expertise made available to us at DeepMind in deep reinforcement learning to explore multi-agent systems in complex environments and use these benchmarks to advance our understanding. Here, we summarise the recent work of our team and present a taxonomy that we feel highlights many important open challenges in multi-agent research.
Collapse
Affiliation(s)
- Ian Gemp
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | | | | | | | | | - Jerome Connor
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | | | | | | | - Romuald Elie
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | | | - Daniel Hennes
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | - Edward Hughes
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | - Mina Khan
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | - Marc Lanctot
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | - Kate Larson
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | - Guy Lever
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | - Siqi Liu
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | - Luke Marris
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | | | - Paul Muller
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | | | - Florian Strub
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | | | | | - Zhe Wang
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| | - Karl Tuyls
- Game Theory & Multi-Agent Team, DeepMind, London, UK
| |
Collapse
|