메뉴 건너뛰기




Volumn 75, Issue 2, 2012, Pages 882-897

Learning efficient Nash equilibria in distributed systems

Author keywords

Completely uncoupled learning; Distributed control; Equilibrium selection; Stochastic stability

Indexed keywords


EID: 84860611398     PISSN: 08998256     EISSN: 10902473     Source Type: Journal    
DOI: 10.1016/j.geb.2012.02.017     Document Type: Article
Times cited : (116)

References (31)
  • 1
    • 84860624477 scopus 로고    scopus 로고
    • Average testing and the efficient boundary. Working paper, University of Oxford, and the Center for Rationality, Hebrew University.
    • Arieli, Itai, Babichenko, Yakov, 2011. Average testing and the efficient boundary. Working paper, University of Oxford, and the Center for Rationality, Hebrew University.
    • (2011)
    • Arieli, I.1    Babichenko, Y.2
  • 3
    • 84860636236 scopus 로고    scopus 로고
    • Completely uncoupled dynamics and Nash equilibria. Working paper 529, Center for the Study of Rationality, Hebrew University.
    • Babichenko, Yakov, 2010a. Completely uncoupled dynamics and Nash equilibria. Working paper 529, Center for the Study of Rationality, Hebrew University.
    • (2010)
    • Babichenko, Y.1
  • 4
    • 84860636240 scopus 로고    scopus 로고
    • How long to Pareto efficiency? Working paper 562, Center for Rationality, Hebrew University.
    • Babichenko, Yakov, 2010b. How long to Pareto efficiency? Working paper 562, Center for Rationality, Hebrew University.
    • (2010)
    • Babichenko, Y.1
  • 5
    • 43949168352 scopus 로고
    • The statistical mechanics of strategic interaction
    • Blume Lawrence E. The statistical mechanics of strategic interaction. Games Econ. Behav. 1993, 4:387-424.
    • (1993) Games Econ. Behav. , vol.4 , pp. 387-424
    • Blume, L.E.1
  • 6
    • 33645073563 scopus 로고
    • The statistical mechanics of best-response strategy revision
    • Blume Lawrence E. The statistical mechanics of best-response strategy revision. Games Econ. Behav. 1995, 11:111-145.
    • (1995) Games Econ. Behav. , vol.11 , pp. 111-145
    • Blume, L.E.1
  • 7
    • 0041657474 scopus 로고    scopus 로고
    • How noise matters
    • Blume Lawrence E. How noise matters. Games Econ. Behav. 2003, 44:251-271.
    • (2003) Games Econ. Behav. , vol.44 , pp. 251-271
    • Blume, L.E.1
  • 8
    • 0036531878 scopus 로고    scopus 로고
    • Multi-agent learning with a variable learning rate
    • Bowling Michael, Veloso Manuel Multi-agent learning with a variable learning rate. Artificial Intelligence 2002, 136:215-250.
    • (2002) Artificial Intelligence , vol.136 , pp. 215-250
    • Bowling, M.1    Veloso, M.2
  • 9
    • 0141838158 scopus 로고    scopus 로고
    • Learning, hypothesis testing, and Nash equilibrium
    • Foster Dean P., Young H.Peyton Learning, hypothesis testing, and Nash equilibrium. Games Econ. Behav. 2003, 45:73-96.
    • (2003) Games Econ. Behav. , vol.45 , pp. 73-96
    • Foster, D.P.1    Young, H.P.2
  • 10
    • 34249003606 scopus 로고    scopus 로고
    • Regret testing: learning to play Nash equilibrium without knowing you have an opponent
    • Foster Dean P., Young H.Peyton Regret testing: learning to play Nash equilibrium without knowing you have an opponent. Theoretical Econ. 2006, 1:341-367.
    • (2006) Theoretical Econ. , vol.1 , pp. 341-367
    • Foster, D.P.1    Young, H.P.2
  • 11
    • 34249059755 scopus 로고    scopus 로고
    • Global convergence of Foster and Young's regret testing
    • Germano Fabrizio, Lugosi Gabor Global convergence of Foster and Young's regret testing. Games Econ. Behav. 2007, 60:135-154.
    • (2007) Games Econ. Behav. , vol.60 , pp. 135-154
    • Germano, F.1    Lugosi, G.2
  • 12
    • 77951634170 scopus 로고    scopus 로고
    • How long to equilibrium? The communication complexity of uncoupled equilibrium procedures
    • Hart Sergiu, Mansour Yishay How long to equilibrium? The communication complexity of uncoupled equilibrium procedures. Games Econ. Behav. 2010, 69:107-126.
    • (2010) Games Econ. Behav. , vol.69 , pp. 107-126
    • Hart, S.1    Mansour, Y.2
  • 13
    • 2942744741 scopus 로고    scopus 로고
    • Uncoupled dynamics do not lead to Nash equilibrium
    • Hart Sergiu, Mas-Colell Andreu Uncoupled dynamics do not lead to Nash equilibrium. Amer. Econ. Rev. 2003, 93:1830-1836.
    • (2003) Amer. Econ. Rev. , vol.93 , pp. 1830-1836
    • Hart, S.1    Mas-Colell, A.2
  • 14
    • 33749642859 scopus 로고    scopus 로고
    • Stochastic uncoupled dynamics and Nash equilibrium
    • Hart Sergiu, Mas-Colell Andreu Stochastic uncoupled dynamics and Nash equilibrium. Games Econ. Behav. 2006, 57:286-303.
    • (2006) Games Econ. Behav. , vol.57 , pp. 286-303
    • Hart, S.1    Mas-Colell, A.2
  • 15
    • 0001963988 scopus 로고
    • Some learning rules for acquiring information
    • Pitman, New York, D.J. McFarland (Ed.)
    • Houston A.I., Kacelnik Alex, McNamara John M. Some learning rules for acquiring information. Functional Ontogeny 1982, Pitman, New York. D.J. McFarland (Ed.).
    • (1982) Functional Ontogeny
    • Houston, A.I.1    Kacelnik, A.2    McNamara, J.M.3
  • 16
    • 0002730095 scopus 로고
    • Learning, mutation, and long-run equilibrium in games
    • Kandori Michihiro, Mailath George, Rob Rafael Learning, mutation, and long-run equilibrium in games. Econometrica 1993, 61:29-56.
    • (1993) Econometrica , vol.61 , pp. 29-56
    • Kandori, M.1    Mailath, G.2    Rob, R.3
  • 18
    • 34249048200 scopus 로고    scopus 로고
    • Multi-agent learning for engineers
    • Mannor Shie, Shamma Jeff S. Multi-agent learning for engineers. Artificial Intelligence 2007, 171:417-422.
    • (2007) Artificial Intelligence , vol.171 , pp. 417-422
    • Mannor, S.1    Shamma, J.S.2
  • 19
    • 84860619529 scopus 로고    scopus 로고
    • Revisiting log-linear learning: asynchrony, completeness and payoff-based implementation. Working Paper, University of Colorado.
    • Marden, Jason R., Shamma, Jeff S., 2008. Revisiting log-linear learning: asynchrony, completeness and payoff-based implementation. Working Paper, University of Colorado.
    • (2008)
    • Marden, J.R.1    Shamma, J.S.2
  • 20
    • 84860636237 scopus 로고    scopus 로고
    • Achieving Pareto optimality through distributed learning. Discussion Paper, University of Colorado and University of Oxford.
    • Marden, Jason R., Young, H. Peyton, Pao, Lucy Y., 2011. Achieving Pareto optimality through distributed learning. Discussion Paper, University of Colorado and University of Oxford.
    • (2011)
    • Marden, J.R.1    Young, H.2    Peyton, P.3    Lucy, Y.4
  • 22
    • 60349123721 scopus 로고    scopus 로고
    • Payoff-based dynamics for multiplayer weakly acyclic games
    • Marden Jason R., Young H.Peyton, Arslan Gurdal, Shamma Jeff S. Payoff-based dynamics for multiplayer weakly acyclic games. SIAM J. Control Optim. 2009, 48(1):373-396.
    • (2009) SIAM J. Control Optim. , vol.48 , Issue.1 , pp. 373-396
    • Marden, J.R.1    Young, H.P.2    Arslan, G.3    Shamma, J.S.4
  • 23
    • 0028987534 scopus 로고
    • Near-far search: an evolutionarily stable foraging strategy
    • Motro Uzi, Shmida Avi Near-far search: an evolutionarily stable foraging strategy. J. Theoretical Biol. 1995, 173:15-22.
    • (1995) J. Theoretical Biol. , vol.173 , pp. 15-22
    • Motro, U.1    Shmida, A.2
  • 24
    • 0034836562 scopus 로고    scopus 로고
    • Algorithms, games and the internet. In: Proceedings of the 33rd Annual ACM Symposium on the Theory of Computing
    • Papadimitriou, Christos, 2001. Algorithms, games and the internet. In: Proceedings of the 33rd Annual ACM Symposium on the Theory of Computing, pp. 749-753.
    • (2001) , pp. 749-753
    • Papadimitriou, C.1
  • 26
    • 0036655913 scopus 로고    scopus 로고
    • Evolutionary implementation and congestion pricing
    • Sandholm W.H. Evolutionary implementation and congestion pricing. Rev. Econ. Stud. 2002, 69:667-689.
    • (2002) Rev. Econ. Stud. , vol.69 , pp. 667-689
    • Sandholm, W.H.1
  • 29
    • 0001944917 scopus 로고
    • The evolution of conventions
    • Young H.Peyton The evolution of conventions. Econometrica 1993, 61:57-84.
    • (1993) Econometrica , vol.61 , pp. 57-84
    • Young, H.P.1
  • 31
    • 59249096487 scopus 로고    scopus 로고
    • Learning by trial and error
    • Young H.Peyton Learning by trial and error. Games Econ. Behav. 2009, 65:626-643.
    • (2009) Games Econ. Behav. , vol.65 , pp. 626-643
    • Young, H.P.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.