23,793 Hits in 9.3 sec

Emergence of Cooperation: State of the Art

Geoff Nitschke
2005 Artificial Life  
An introduction and overview of emergent cooperation in artificial life is presented, followed by a survey of emergent cooperation in swarm-based systems, the pursuit-evasion domain and robo-cup soccer  ...  The article concludes that current studies in emergent cooperative behavior are limited by a lack of situated and embodied approaches, and the research infancy of current biologically inspired design approaches  ...  agents followed simple local rules.  ... 
doi:10.1162/1064546054407194 pmid:16053576 fatcat:4sznnxnyuffgdlavqmse6eyvba

Coordinated exploration of unknown labyrinthine environments applied to the pursuit evasion problem

Damien Pellier, Humbert Fiorino
2005 Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems - AAMAS '05  
This paper introduces a multi-robot cooperation approach to solve the "pursuit evasion" problem for mobile robots that have omnidirectional vision sensors in unknown environments.  ...  The main characteristic of this approach is based on the robots cooperation by sharing knowledge and making them work as a team: a complete algorithm for computing robots motion strategy is presented as  ...  This case is shown by the simple example in figure 9 . Implementation. The implementation was carried out with JAVA language on the multi-agent platform JADE.  ... 
doi:10.1145/1082473.1082609 dblp:conf/atal/PellierF05 fatcat:72boxxi2efeuteei3335zh62jy

Game-theoretic Utility Tree for Multi-Robot Cooperative Pursuit Strategy [article]

Qin Yang, Ramviyas Parasuraman
2022 arXiv   pre-print
This paper proposes and extends the new hierarchical network-based model, termed Game-theoretic Utility Tree (GUT), to arrive at a cooperative pursuit strategy to catch an evader in the Pursuit-Evasion  ...  The experiments demonstrated the effectiveness of the GUT, and the performances validated that the GUT could effectively organize cooperation strategies, helping the group with fewer advantages achieve  ...  It combines with a new payoff measure based on agent needs [31] for real-time strategy games and provides a novel method to organize agents' group behaviors in the Pursuit domain.  ... 
arXiv:2206.01109v1 fatcat:nxkea2cyobej3kob4qrexvy5ha

Multiagent Cooperative Learning Strategies for Pursuit-Evasion Games

Jong Yih Kuo, Hsiang-Fu Yu, Kevin Fong-Rey Liu, Fang-Wen Lee
2015 Mathematical Problems in Engineering  
Two kinds of pursuit strategies are proposed, one for agents that cooperate with each other and the other for agents that operate independently.  ...  This study examines the pursuit-evasion problem for coordinating multiple robotic pursuers to locate and track a nonadversarial mobile evader in a dynamic environment.  ...  A multiagent pursuit-evasion game involves guiding one group of agents (pursuers) to cooperate with each other to catch another group of agents (evaders).  ... 
doi:10.1155/2015/964871 fatcat:eh247dsvvvhwphu4ydfkcqhojm

Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems

Laetitia Matignon, Guillaume J. Laurent, Nadine Le Fort-Piat
2012 Knowledge engineering review (Print)  
A selection of multi-agent domains is classified according to those challenges: matrix games, Boutilier's coordination game, predators pursuit domains and a special multi-state game.  ...  In the framework of fully cooperative multi-agent systems, independent (non-communicative) agents that learn by reinforcement must overcome several difficulties to manage to coordinate.  ...  Indeed, even a simple game with two players and few actions can be challenging if agents are unaware of the game and independent (Abdallah & Lesser, 2008) .  ... 
doi:10.1017/s0269888912000057 fatcat:j2unyb75c5a3lmpvdny3ex77ei

An Interaction Game Framework for the Investigation of Human–Agent Cooperation [chapter]

Philipp Kulms, Nikita Mattar, Stefan Kopp
2015 Lecture Notes in Computer Science  
Success in human-agent interaction will to a large extent depend on the ability of the system to cooperate with humans over repeated tasks.  ...  To explore these questions, we present a new interaction game framework that is centered around a collaborative puzzle game and goes beyond commonly adopted scenarios like the Prisoner's dilemma.  ...  Fig. 1 . 1 Concept of the puzzle game interface with a virtual agent as cooperation partner. The agent can display multimodal behavior or other contextual social cues.  ... 
doi:10.1007/978-3-319-21996-7_43 fatcat:zrjbuxsogramrbdawbg2x5mxw4

Making friends on the fly: Cooperating with new teammates

Samuel Barrett, Avi Rosenfeld, Sarit Kraus, Peter Stone
2017 Artificial Intelligence  
This problem motivates the area of ad hoc teamwork in which an agent may potentially cooperate with a variety of teammates in order to achieve a shared goal.  ...  This article focuses on a limited version of the ad hoc teamwork problem in which an agent knows the environmental dynamics and has had past experiences with other teammates, though these experiences may  ...  Acknowledgments This work has taken place in the Learning Agents Research Group (LARG) at the Artificial Intelligence Laboratory, The University of Texas at Austin.  ... 
doi:10.1016/j.artint.2016.10.005 fatcat:ezxvbpjmszcrblqlnh6h6ye3xe

Cooperation in evolutionary games on complex networks

Jianlei Zhang, Chunyan Zhang, Tianguang Chu, Zhifu Chen
2010 49th IEEE Conference on Decision and Control (CDC)  
We consider a population engaged in continuous public goods games.  ...  In our study, the lowest contributor in each game will be removed from the group, meanwhile new players will be added to the network to maintain the constant population size.  ...  Evolutionary game theory has presented a competent framework for investigating the emergence and evolution of cooperation among selfish agents [1] - [9] .  ... 
doi:10.1109/cdc.2010.5717077 dblp:conf/cdc/ZhangZCC10 fatcat:obcy6q7w45fdzgq7ulg5aoylv4

Cooperative coevolution of real predator robots and virtual robots in the pursuit domain [article]

Lijun Sun, Chao Lyu, Yuhui Shi
2019 arXiv   pre-print
The pursuit domain, or predator-prey problem is a standard testbed for the study of coordination techniques.  ...  This paper presents a particle swarm optimization (PSO) based cooperative coevolutionary algorithm for the predator robots, called CCPSO-R, where real and virtual robots coexist for the first time in an  ...  The pursuit / predator-prey domain Generally speaking, the pursuit domain problem is a game where predators try to capture the prey with or without coordination.  ... 
arXiv:1901.07865v1 fatcat:xhqsneh4gjes5prtzwqg3jrwea

Cooperative Multi-agent Control Using Deep Reinforcement Learning [chapter]

Jayesh K. Gupta, Maxim Egorov, Mykel Kochenderfer
2017 Lecture Notes in Computer Science  
We introduce a set of cooperative control tasks that includes tasks with discrete and continuous actions, as well as tasks that involve hundreds of agents.  ...  Using deep reinforcement learning with a curriculum learning scheme, our approach can solve problems that were previously considered intractable by most multi-agent reinforcement learning algorithms.  ...  INTRODUCTION Learning to cooperate between several interacting agents has been well studied [39, 30, 6] .  ... 
doi:10.1007/978-3-319-71682-4_5 fatcat:ie4vvneipjgxbdwngj3bncs6eu

Multi Agent Deep Learning with Cooperative Communication

David Simões, Nuno Lau, Luís Paulo Reis
2020 Journal of Artificial Intelligence and Soft Computing Research  
AbstractWe consider the problem of multi agents cooperating in a partially-observable environment. Agents must learn to coordinate and share relevant information to solve the tasks successfully.  ...  This article describes Asynchronous Advantage Actor-Critic with Communication (A3C2), an end-to-end differentiable approach where agents learn policies and communication protocols simultaneously.  ...  In the Pursuit game, map exploration also improves and agents coordinate to surround and capture prey as soon as any predator finds it.  ... 
doi:10.2478/jaiscr-2020-0013 fatcat:oehr25sfardffihup2goyrqyoa

Cooperative Games with Overlapping Coalitions

G. Chalkiadakis, E. Elkind, E. Markakis, M. Polukarov, N. R. Jennings
2010 The Journal of Artificial Intelligence Research  
To tackle such scenarios, we introduce a model for cooperative games with overlapping coalitions—or overlapping coalition formation (OCF) games.  ...  In the usual models of cooperative game theory, the outcome of a coalition formation process is either the grand coalition or a coalition structure that consists of disjoint coalitions.  ...  Introduction Coalition formation, widely studied in game theory and economics (Myerson, 1991) , has attracted much attention in AI as means of forming teams of autonomous selfish agents that need to cooperate  ... 
doi:10.1613/jair.3075 fatcat:66ziawqsmbfirbugksbioosjjy

Novelty-Driven Cooperative Coevolution

Jorge Gomes, Pedro Mariano, Anders Lyhne Christensen
2017 Evolutionary Computation  
CCEAs enable, for instance, the evolution of cooperative multiagent systems composed of heterogeneous agents, where each agent is modelled as a component of the solution.  ...  Novelty-driven cooperative coevolution can substantially increase the potential of CCEAs while maintaining a computational complexity that scales well with the number of populations.  ...  Pursuit tasks involve a number of agents (predators) chasing a prey. The predators cannot move faster than the prey, and they therefore need to cooperate in order to successfully capture the prey.  ... 
doi:10.1162/evco_a_00173 pmid:26652102 fatcat:uq7shltukzdgvpe2nuu4vhvogi

Cooperative Multi-Agent Learning: The State of the Art

Liviu Panait, Sean Luke
2005 Autonomous Agents and Multi-Agent Systems  
We provide a broad survey of the cooperative multi-agent learning literature.  ...  In this survey we attempt to draw from multi-agent learning work in a spectrum of areas, including reinforcement learning, evolutionary computation, game theory, complex systems, agent modeling, and robotics  ...  Pursuit games consist of a number of agents (predators) cooperatively chasing a prey.  ... 
doi:10.1007/s10458-005-2631-2 fatcat:u3xlftotajfitdtfmvbmggwgbi

The evolution of cooperation in spatial groups

Jianlei Zhang, Chunyan Zhang, Tianguang Chu
2011 Chaos, Solitons & Fractals  
Inspired by this observation, we propose a simple model of evolutionary public goods games in which individuals are organized into networked groups.  ...  Individuals establish public goods games with partners in the same group and migrate among neighboring groups depending on their payoffs and expectations.  ...  The migration rule allows agents with unsatisfactory gains to seek new groups with more altruists to pursuit higher payoffs than before.  ... 
doi:10.1016/j.chaos.2011.01.002 fatcat:zdfvicxwsnb5nbuwjzx6daetnm
« Previous Showing results 1 — 15 out of 23,793 results