Developing, evaluating and scaling learning agents in multi-agent environments

被引：2

作者：

Gemp, Ian ^{[1
]}

Anthony, Thomas ^{[1
]}

Bachrach, Yoram ^{[1
]}

Bhoopchand, Avishkar ^{[1
]}

Bullard, Kalesha ^{[1
]}

Connor, Jerome ^{[1
]}

Dasagi, Vibhavari ^{[1
]}

De Vylder, Bart ^{[1
]}

Duenez-Guzman, Edgar A. ^{[1
]}

Elie, Romuald ^{[1
]}

Everett, Richard ^{[1
]}

Hennes, Daniel ^{[1
]}

Hughes, Edward ^{[1
]}

Khan, Mina ^{[1
]}

Lanctot, Marc ^{[1
]}

Larson, Kate ^{[1
]}

Lever, Guy ^{[1
]}

Liu, Siqi ^{[1
]}

Marris, Luke ^{[1
]}

McKee, Kevin R. ^{[1
]}

Muller, Paul ^{[1
]}

Perolat, Julien ^{[1
]}

Strub, Florian ^{[1
]}

Tacchetti, Andrea ^{[1
]}

Tarassov, Eugene ^{[1
]}

Wang, Zhe ^{[1
]}

Tuyls, Karl ^{[1
]}

机构：

[1] DeepMind, Game Theory & Multiagent Team, London, England

来源：

AI COMMUNICATIONS | 2022年 / 35卷 / 04期

关键词：

Game theory; multi-agent; reinforcement learning; equilibrium; mechanism design; REINFORCEMENT; DYNAMICS; GAMES;

D O I：

10.3233/AIC-220113

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：271 / 284

页数：14

共 50 条

[1] Evaluating the Coordination of Agents in Multi-agent Reinforcement Learning
Barton, Sean L.
Zaroukian, Erin
Asher, Derrik E.
Waytowich, Nicholas R.
[J]. INTELLIGENT HUMAN SYSTEMS INTEGRATION 2019, 2019, 903 : 765 - 770
[2] Using and re-using agents in multi-agent learning environments
Paiva, A
Machado, I
Martins, A
[J]. ARTIFICIAL INTELLIGENCE IN EDUCATION: OPEN LEARNING ENVIRONMENTS: NEW COMPUTATIONAL TECHNOLOGIES TO SUPPORT LEARNING, EXPLORATION AND COLLABORATION, 1999, 50 : 750 - 752
[3] AUTOTELIC REINFORCEMENT LEARNING IN MULTI-AGENT ENVIRONMENTS
Nisioti, Eleni
Masquil, Elias
Hamon, Gautier
Moulin-Frier, Clement
[J]. CONFERENCE ON LIFELONG LEARNING AGENTS, VOL 232, 2023, 232 : 137 - 161
[4] Modelling Learning Experiences in adaptive multi-agent learning environments
Tsatsou, Dorothea
Vretos, Nicholas
Daras, Petros
[J]. 2017 9TH INTERNATIONAL CONFERENCE ON VIRTUAL WORLDS AND GAMES FOR SERIOUS APPLICATIONS (VS-GAMES), 2017, : 193 - 200
[5] Rating the skill of synthetic agents in competitive multi-agent environments
Kiourt, Chairi
Kalles, Dimitris
Pavlidis, George
[J]. KNOWLEDGE AND INFORMATION SYSTEMS, 2019, 58 (01) : 35 - 58
[6] Rating the skill of synthetic agents in competitive multi-agent environments
Chairi Kiourt
Dimitris Kalles
George Pavlidis
[J]. Knowledge and Information Systems, 2019, 58 : 35 - 58
[7] Robust multi-agent reinforcement learning for noisy environments
Chen, Xinning
Liu, Xuan
Luo, Canhui
Yin, Jiangjin
[J]. PEER-TO-PEER NETWORKING AND APPLICATIONS, 2022, 15 (02) : 1045 - 1056
[8] Smart Environments for Learning Multi-Agent Systems Approach
Mikulecky, Peter
[J]. PROCEEDINGS OF THE 12TH EUROPEAN CONFERENCE ON E-LEARNING (ECEL 2013), 2013, : 304 - 310
[9] Centralized reinforcement learning for multi-agent cooperative environments
Chengxuan Lu
Qihao Bao
Shaojie Xia
Chongxiao Qu
[J]. Evolutionary Intelligence, 2024, 17 : 267 - 273
[10] Centralized reinforcement learning for multi-agent cooperative environments
Lu, Chengxuan
Bao, Qihao
Xia, Shaojie
Qu, Chongxiao
[J]. EVOLUTIONARY INTELLIGENCE, 2024, 17 (01) : 267 - 273

← 1 2 3 4 5 →