Open AccessProceedings Article
Learning cooperative games
Maria-Florina Balcan,Ariel D. Procaccia,Yair Zick +2 more
- 25 Jul 2015
- Vol. 2015, pp 475-481
TL;DR: A novel connection between PAC learnability and core stability is established: for games that are efficiently learnable, it is possible to find payoff divisions that are likely to be stable using a polynomial number of samples.
read more
Abstract: This paper explores a PAC (probably approximately correct) learning model in cooperative games Specifically, we are given m random samples of coalitions and their values, taken from some unknown cooperative game; can we predict the values of unseen coalitions? We study the PAC learnability of several well-known classes of cooperative games, such as network flow games, threshold task games, and induced subgraph games We also establish a novel connection between PAC learnability and core stability: for games that are efficiently learnable, it is possible to find payoff divisions that are likely to be stable using a polynomial number of samples
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Proceedings Article
Statistical Cost Sharing
Eric Balkanski,Umar Syed,Sergei Vassilvitskii +2 more
- 01 Mar 2017
TL;DR: In this paper, the cost sharing problem for cooperative games is studied in the setting where the cost function C is not available via oracle queries, but must instead be learned from samples drawn from a distribution, represented as tuples (S, C(S)), for different subsets S of players.
•Posted Content
Learning Adversary Behavior in Security Games: A PAC Model Perspective
TL;DR: In this paper, a PAC model is proposed to directly learn the response function of the adversary in Stackelberg security games, where the learned adversary model is used to plan the defender's strategy.
24
Learning Adversary Behavior in Security Games: A PAC Model Perspective
Arunesh Sinha,Debarun Kar,Milind Tambe +2 more
- 09 May 2016
TL;DR: In this article, a PAC model is proposed to directly learn the response function of the adversary in Stackelberg security games, and the learned adversary model is used to plan the defender's strategy.
21
Emergent Prosociality in Multi-Agent Games Through Gifting
Woodrow Z. Wang,Mark Beliaev,Erdem Bıyık,Daniel A. Lazar,Ramtin Pedarsani,Dorsa Sadigh +5 more
- 09 Aug 2021
TL;DR: In this paper, a less restrictive peer-rewarding mechanism, gifting, is proposed to guide the agents toward more socially desirable equilibria while allowing agents to remain selfish and decentralized.
•Dissertation
Approximate Pure Nash Equilibria in Congestion, Opinion Formation and Facility Location Games
Matthias Feldotto
- 01 Jan 2019
TL;DR: This thesis investigates approximate pure Nash equilibria in different game-theoretic models and bound the approximation guarantees for natural states nearly independent of the specific definition of the players' neighborhoods by applying a concept of virtual costs.
11
References
•Book
Neural Network Learning: Theoretical Foundations
Martin Anthony,Peter L. Bartlett +1 more
- 01 Nov 1999
TL;DR: The authors explain the role of scale-sensitive versions of the Vapnik Chervonenkis dimension in large margin classification, and in real prediction, and discuss the computational complexity of neural network learning.
2K
•Book
An Introduction to Computational Learning Theory
Michael Kearns,Umesh Vazirani +1 more
- 01 Jan 1994
TL;DR: The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata is described.
2K
Graphs and Cooperation in Games
TL;DR: Graph-theoretic ideas are used to analyze cooperation structures in games, and fair allocation rules are proven to be unique, closely related to the Shapley value, and stable for a wide class of games.
•Book
Introduction to the Theory of Cooperative Games
Bezalel Peleg,Peter Sudhölter +1 more
- 01 Dec 1983
TL;DR: In this paper, the main solutions of cooperative games, including the core, bargaining set, kernel, nucleolus, and the Shapley value of TU games, are investigated in detail.
773
On the complexity of cooperative solution concepts
TL;DR: The von Neumann-Morgenstern solution is pointed out that its existence may not even be decidable, and many of these results generalize to the case in which the game is presented by a hypergraph with edges of size k > 2.
762
Related Papers (5)
Eric Balkanski,Umar Syed,Sergei Vassilvitskii +2 more
- 01 Mar 2017
Haris Aziz,Felix Brandt,Paul Harrenstein +2 more
- 10 May 2010
Morton Davis,Michael Maschler +1 more