A Link between Sequential Semi-anonymous Nonatomic Games and their Large Finite Counterparts
We show that equilibria of a sequential semi-anonymous nonatomic game (SSNG) can be adopted by players in corresponding large but finite dynamic games to achieve near-equilibrium payoffs. Such equilibria in the form of random state-to-action rules are parsimonious in form and easy to execute, as they are both oblivious of past history and blind to other players' present states. Our transient results can be extended to a stationary case, where the finite counterparts are special discounted stochastic games. The kind of equilibria we adopt for SSNG are similar to distributional equilibria that are well understood in literature, and they themselves are shown to exist.
Code (0)
등록된 구현이 없습니다.
Tasks
FormSimilar Papers 제목 키워드 기반
Learning in nonatomic games, Part I: Finite action spaces and population games
We examine the long-run behavior of a wide range of dynamics for learning in nonatomic games, in both discrete and continuous time. The class of dynamics under consideration includes fictitious play and its regularized v…
Social Learning in Nonatomic Routing Games
We consider a discrete-time nonatomic routing game with variable demand and uncertain costs. Given a routing network with single origin and destination, the cost function of each edge depends on some uncertain persistent…
Full Implementation via Information Design in Nonatomic Games
This paper studies the implementation of Bayes correlated equilibria in symmetric Bayesian nonatomic games, using direct information structures and obedient strategies. The main results demonstrate full implementation in…
AllExit-and-Join Dynamics and Equilibrium in Continuum Cooperative Games
This paper develops a continuum theory of exit-and-join coalition dynamics in nonatomic cooperative games. We extend the Aumann-Shapley value and the Aumann-Drèze value to coalition structures in which each coalition is …
Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach
Few-shot inductive link prediction on knowledge graphs (KGs) aims to predict missing links for unseen entities with few-shot links observed. Previous methods are limited to transductive scenarios, where entities exist in…
Inductive Link PredictionKnowledge GraphsLink PredictionPrediction