Home > Research > Publications & Outputs > Equilibrium selection in potential games with n...
View graph of relations

Equilibrium selection in potential games with noisy rewards

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Equilibrium selection in potential games with noisy rewards. / Leslie, David S.; Marden, Jason R.
Network Games, Control and Optimization (NetGCooP), 2011 5th International Conference on. IEEE, 2011. p. 1-4.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Leslie, DS & Marden, JR 2011, Equilibrium selection in potential games with noisy rewards. in Network Games, Control and Optimization (NetGCooP), 2011 5th International Conference on. IEEE, pp. 1-4. <http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6103872>

APA

Leslie, D. S., & Marden, J. R. (2011). Equilibrium selection in potential games with noisy rewards. In Network Games, Control and Optimization (NetGCooP), 2011 5th International Conference on (pp. 1-4). IEEE. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6103872

Vancouver

Leslie DS, Marden JR. Equilibrium selection in potential games with noisy rewards. In Network Games, Control and Optimization (NetGCooP), 2011 5th International Conference on. IEEE. 2011. p. 1-4

Author

Leslie, David S. ; Marden, Jason R. / Equilibrium selection in potential games with noisy rewards. Network Games, Control and Optimization (NetGCooP), 2011 5th International Conference on. IEEE, 2011. pp. 1-4

Bibtex

@inproceedings{83499f9d8d2e479e87075d5a552fcfa4,
title = "Equilibrium selection in potential games with noisy rewards",
abstract = "Game theoretical learning in potential games is a highly active research area stemming from the connection between potential games and distributed optimisation. In many settings an optimisation problem can be represented by a potential game where the optimal solution corresponds to the potential function maximizer. Accordingly, significant research attention has focused on the design of distributed learning algorithms that guarantee convergence to the potential maximizer in potential games. However, there are currently no existing algorithms that provide convergence to the potential function maximiser when utility functions are corrupted by noise. In this paper we rectify this issue by demonstrating that a version of payoff-based loglinear learning guarantees that the only stochastically stable states are potential function maximisers even in noisy settings.",
author = "Leslie, {David S.} and Marden, {Jason R.}",
year = "2011",
language = "English",
isbn = "9781467303835",
pages = "1--4",
booktitle = "Network Games, Control and Optimization (NetGCooP), 2011 5th International Conference on",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Equilibrium selection in potential games with noisy rewards

AU - Leslie, David S.

AU - Marden, Jason R.

PY - 2011

Y1 - 2011

N2 - Game theoretical learning in potential games is a highly active research area stemming from the connection between potential games and distributed optimisation. In many settings an optimisation problem can be represented by a potential game where the optimal solution corresponds to the potential function maximizer. Accordingly, significant research attention has focused on the design of distributed learning algorithms that guarantee convergence to the potential maximizer in potential games. However, there are currently no existing algorithms that provide convergence to the potential function maximiser when utility functions are corrupted by noise. In this paper we rectify this issue by demonstrating that a version of payoff-based loglinear learning guarantees that the only stochastically stable states are potential function maximisers even in noisy settings.

AB - Game theoretical learning in potential games is a highly active research area stemming from the connection between potential games and distributed optimisation. In many settings an optimisation problem can be represented by a potential game where the optimal solution corresponds to the potential function maximizer. Accordingly, significant research attention has focused on the design of distributed learning algorithms that guarantee convergence to the potential maximizer in potential games. However, there are currently no existing algorithms that provide convergence to the potential function maximiser when utility functions are corrupted by noise. In this paper we rectify this issue by demonstrating that a version of payoff-based loglinear learning guarantees that the only stochastically stable states are potential function maximisers even in noisy settings.

M3 - Conference contribution/Paper

SN - 9781467303835

SP - 1

EP - 4

BT - Network Games, Control and Optimization (NetGCooP), 2011 5th International Conference on

PB - IEEE

ER -