Access the full text.
Sign up today, get DeepDyve free for 14 days.
ACM Transactions on Autonomous and Adaptive Systems
M. Osborne, Ariel Rubinstein (1995)
A Course in Game Theory, 1
P. Hoen, K. Tuyls, Liviu Panait, S. Luke, H. Poutré (2005)
An Overview of Cooperative and Competitive Multiagent Learning
(2013)
Received January
Daniel Villatoro, J. Sabater-Mir, S. Sen (2011)
Social Instruments for Robust Convention Emergence
S. Sen, S. Airiau (2007)
Emergence of Norms through Social Learning
R. Riolo, Michael Cohen, R. Axelrod (2001)
Evolution of cooperation without reciprocityNature, 414
T. Kura, K. Yoda (2001)
Can voluntary nutritional gifts in seminal flow evolve?Journal of Ethology, 19
John Smith (1982)
Evolution and the Theory of Games
David Hales (2000)
Cooperation without Memory or Space: Tags, Groups and the Prisoner's Dilemma
Michael Bowling, M. Veloso (2002)
Multiagent learning using a variable learning rateArtif. Intell., 136
K. Verbeeck, A. Nowé, Johan Parent, K. Tuyls (2007)
Exploring selfish reinforcement learning in repeated games with stochastic rewardsAutonomous Agents and Multi-Agent Systems, 14
Vincent Conitzer, T. Sandholm (2003)
AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponentsMachine Learning, 67
A. Greenwald, Keith Hall (2003)
Correlated Q-Learning
Jianye Hao, Ho-fung Leung (2011)
Learning to Achieve Social Rationality Using Tag Mechanism in Repeated Interactions2011 IEEE 23rd International Conference on Tools with Artificial Intelligence
Junling Hu, Michael Wellman (1998)
Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm
L. Hogg, N. Jennings (2001)
Socially intelligent reasoning for autonomous agentsIEEE Trans. Syst. Man Cybern. Part A, 31
J. Holland, K. Holyoak, R. Nisbett, Paul Thagard, S. Smoliar (1987)
Induction: Processes of Inference, Learning, and DiscoveryIEEE Expert, 2
J. Crandall, M. Goodrich (2005)
Learning to Teach and Follow in Repeated Games
(1992)
Mach. Learn
J. Pitt, J. Schaumeier, D. Busquets, S. Macbeth (2012)
Self-Organising Common-Pool Resource Allocation and Canons of Distributive Justice2012 IEEE Sixth International Conference on Self-Adaptive and Self-Organizing Systems
Austin McDonald, S. Sen (2005)
The Success and Failure of Tag-Mediated Evolution of Cooperation
Matthew Matlock, S. Sen (2009)
Effective tag mechanisms for evolving cooperation
David Hales, B. Edmonds (2003)
Evolving social rationality for MAS using "tags"
Jianye Hao, Ho-fung Leung (2012)
Learning to Achieve Socially Optimal Solutions in General-Sum Games
C. Claus, Craig Boutilier (1998)
The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems
Matthew Matlock, S. Sen (2007)
Effective tag mechanisms for evolving coordination
L. Hogg, N. Jennings (1997)
Socially Rational Agents
M. Littman (1994)
Markov Games as a Framework for Multi-Agent Reinforcement Learning
S. Kapetanakis, D. Kudenko (2002)
Reinforcement learning of coordination in cooperative multi-agent systems
Jianye Hao, Ho-fung Leung (2010)
Strategy and Fairness in Repeated Two-agent Interaction2010 22nd IEEE International Conference on Tools with Artificial Intelligence, 2
E. Howley, C. O'Riordan (2005)
The emergence of cooperation among agents using simple fixed bias tagging2005 IEEE Congress on Evolutionary Computation, 2
R. Brafman, Moshe Tennenholtz (2004)
Efficient learning equilibrium
P. Allison (1992)
The Cultural Evolution of Beneficent NormsSocial Forces, 71
J. Wakano, Norio Yamamura (2001)
A simple learning strategy that realizes robust cooperation better than Pavlov in Iterated Prisoners' DilemmaJournal of Ethology, 19
Liviu Panait, S. Luke (2005)
Cooperative Multi-Agent Learning: The State of the ArtAutonomous Agents and Multi-Agent Systems, 11
M. Nowak, K. Sigmund (1993)
A strategy of win-stay, lose-shift that outperforms tit-for-tat in the Prisoner's Dilemma gameNature, 364
Achieving Socially Optimal Outcomes in Multiagent Systems with Reinforcement Social Learning JIANYE HAO and HO-FUNG LEUNG, The Chinese University of Hong Kong In multiagent systems, social optimality is a desirable goal to achieve in terms of maximizing the global efficiency of the system. We study the problem of coordinating on socially optimal outcomes among a population of agents, in which each agent randomly interacts with another agent from the population each round. Previous work [Hales and Edmonds 2003; Matlock and Sen 2007, 2009] mainly resorts to modifying the interaction protocol from random interaction to tag-based interactions and only focus on the case of symmetric games. Besides, in previous work the agents' decision making processes are usually based on evolutionary learning, which usually results in high communication cost and high deviation on the coordination rate. To solve these problems, we propose an alternative social learning framework with two major contributions as follows. First, we introduce the observation mechanism to reduce the amount of communication required among agents. Second, we propose that the agents' learning strategies should be based on reinforcement learning technique instead of evolutionary learning. Each agent explicitly keeps the record of its current state in its learning
ACM Transactions on Autonomous and Adaptive Systems (TAAS) – Association for Computing Machinery
Published: Sep 1, 2013
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.