## Learning to Play Network Games (1997)

Citations: | 10 - 8 self |

### BibTeX

@MISC{Greenwald97learningto,

author = {Amy Greenwald},

title = {Learning to Play Network Games},

year = {1997}

}

### OpenURL

### Abstract

this paper, the common knowledge assumptions are dropped in varying capacities, thereby limiting the credibility of the Nash equilibrium solution concept in its usual form. This research focuses on alternative forms of equilibria which arise as a result of learning in repeated games in the absence of common knowledge. Without the assumptions of common knowledge of rationality and payoff structure, games are not conducive to deductive solutions, such as Nash equilibrium. One of the focal points of modern game theory is inductive reasoning in repeated games, which is described as follows in Arthur [1]: Each agent keeps track of the performance of a private collection of belief-models. When it comes time to make choices, he acts upon his currently most credible (or possibly most profitable) one. The others he keeps at the back of his mind, so to speak. Alternatively, he may act upon a combination of several...Once actions are taken, agents update the track record of all their hypotheses. This type of reasoning is known as belief-based learning. Examples of beliefbaser learning algorithms include Bayesian updating and calibration. Under certain conditions, Bayesian learning converges to Nash equilibrium, while calibrated learning always converges to a generalization of Nash equilibrium known as correlated equilibrium. The intent of this thesis research is to develop efficient learning algorithms which quickly converge to reasonable approximations of equilibria in game-theoretic models of network routing and congestion problems. 2 Nash Equilibrium

### Citations

8563 | Elements of Information Theory - Cover, Thomas - 1991 |

1496 | M.: Reasoning about Knowledge - Fagin, Halpern, et al. - 1995 |

778 |
Evolution and the Theory of Games
- Smith, J
- 1982
(Show Context)
Citation Context ...The payoffs of this coordination game are shown in Figure 3; the woman is player 1 and the man is player 2. The last example that is presented is an ecological game which was studied by Maynard Smith =-=[15]-=- in his analysis of the theory of evolution in terms of games. The game is played between animals of similar physique who live in the wilderness and encounter one another in their search for prey. Dur... |

727 |
The Evolution of Cooperation. Basic
- Axelrod
- 1984
(Show Context)
Citation Context ...n strategic form games of complete information. 2.1 Examples The most well-known game-theoretic scenario is the paradoxical situation known as the Prisoner's Dilemma, which was popularized by Axelrod =-=[5]-=- in his popular science book. The following is one variant of the story from which this game derives it name.1 An awful crime has been committed for which two suspects are being held incommunicado. Th... |

669 | The weighted majority algorithm - LITTLESTONE, WARMUTH - 1994 |

293 | Correlated equilibrium as an expression of Bayesian rationality - Aumann - 1987 |

215 | Rational Learning leads to Nash Equilibrium - Kalain, Lehrer - 1993 |

143 | Epistemic Conditions for Nash Equilibrium - Aumann, Brandenburger - 1995 |

134 | Game theory, on-line prediction and boosting - Freund, Schapire - 1996 |

127 | Neumann and Oskar Morgenstern. Theory of Games and Economic Behavior - von - 1947 |

75 |
The well calibrated Bayesian
- DAWID
- 1982
(Show Context)
Citation Context ...re conditioned on those beliefs. Calibration is weaker than merging; thus, calibrated learning processes converge to a more general equilibrium concept than Nash, namely correlated equilibrium. Dawid =-=[7]-=- gives the following intuitive description of calibration: Suppose that, in a long sequence of weather forecasts, we look at all those days for which the forecast probability of precipitation was, say... |

59 | Lectures on Game Theory - Aumann - 1989 |

30 | Two-Person Game Theory, The
- Rapoport
- 1966
(Show Context)
Citation Context ...rix which describes the Prisoner's Dilemma is depicted in Figure 1, with C denoting "confess", or "cooperate", and D denoting "don't confess", or "defect". 1For the usual interpretation, see Rapoport =-=[14]-=-, the two-time winner of the Prisoner's Dilemma computer tournament organized by Axelrod. 3sC D 4,4 0,5 1,15,0 DC1 2 Figure 1: The Prisoner's Dilemma 1 2 H T H T 1,-1 -1,1 -1,1 1,-1 Figure 2: Matching... |

13 |
Inductive reasoning and bounded rationality. Complexity in Economic Theory
- Arthur
- 1994
(Show Context)
Citation Context ...mes are not conducive to deductive solutions, such as Nash equilibrium. One of the focal points of modern game theory is inductive reasoning in repeated games, which is described as follows in Arthur =-=[1]-=-: Each agent keeps track of the performance of a private collection of belief-models. When it comes time to make choices, he acts upon his currently most credible (or possibly most profitable) one. Th... |

5 | Learning with hazy beliefs - Foster, Young - 1996 |

4 | AND RAKESH V. VOHRA: Calibrated learning and correlated equilibrium - FOSTER - 1997 |

4 | Issues and challenges in atm networks - Vetter, Du - 1995 |