Corpus ID: 237532317

Learning Noisy Hedonic Games

  title={Learning Noisy Hedonic Games},
  author={Prashant Trivedi and Nandyala Hemachandra},
We consider the learning task of prediction of formation of core stable coalition structure in hedonic games based on agents’ noisy preferences. We have considered two cases: complete information (noisy preferences of all the agents are entirely known) and partial information (noisy preferences over some coalitions are only known). We introduce a noise model that probabilistically scales the valuations of coalitions. The performance metric is the probability of our prediction conditioned on all… Expand

Figures from this paper


Learning Hedonic Games
Coalitional stability in hedonic games has usually been considered in the setting where agent preferences are fully known. We consider the setting where agent preferences are unknown; we lay theExpand
Hedonic coalition nets
Hedonic coalition nets are shown to be universally expressive, yet are at least as succinct as other existing representation schemes for hedonic games, and the complexity of many natural decision problems for these games are investigated. Expand
The Stability of Hedonic Coalition Structures
This work considers the partitioning of a society into coalitions in purely hedonic settings, and shows that if coalitions can be ordered according to some characteristic over which players have single-peaked preferences, then there exists an individually stable coalition partition. Expand
Fractional Hedonic Games
This article proposes a number of conditions under which the core of FHGs is non-empty and provides algorithms for computing a core stable outcome and shows that the core may be empty in other cases, and that it is computationally hard in general to decide non-emptiness of the core. Expand
Cooperative Game Solution Concepts that Maximize Stability under Noise
This work investigates which solution concepts maximize the probability of ex-post stability (after the true values are revealed), and shows how various conditions on the noise characterize the least core and the nucleolus as optimal. Expand
Existence of stability in hedonic coalition formation games
It is shown that the existence results cannot be strengthened to the case of stronger known stability concepts, and preference restrictions pertain to top responsiveness and bottom responsiveness which model optimistic and pessimistic behavior of players respectively. Expand
Learning Cooperative Games
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. Expand
NP-completeness in hedonic games
It is demonstrated that the core, the Nash stable set and the individually stable set have corresponding NP -complete decision problems for a variety of situations and, hence, that only exponential-time (slow) algorithms are known for solving them. Expand
Statistical Cost Sharing
We study the cost sharing problem for cooperative games in situations where the cost function C is not available via oracle queries, but must instead be learned from samples drawn from aExpand
Core in a simple coalition formation game
The core of a class of coalition formation game in which every player's payoff depends only on the members of her coalition is analyzed, and two top-coalition properties each of which guarantee the existence of a core allocation are introduced. Expand