Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Faizal, Fathima Zarin"'
We study best-response type learning dynamics for two player zero-sum matrix games. We consider two settings that are distinguished by the type of information that each player has about the game and their opponent's strategy. The first setting is the
Externí odkaz:
http://arxiv.org/abs/2407.20128
Autor:
Faizal, Fathima Zarin, Borkar, Vivek
Two time scale stochastic approximation algorithms emulate singularly perturbed deterministic differential equations in a certain limiting sense, i.e., the interpolated iterates on each time scale approach certain differential equations in the large
Externí odkaz:
http://arxiv.org/abs/2306.05723
We study the problem of best-arm identification in a distributed variant of the multi-armed bandit setting, with a central learner and multiple agents. Each agent is associated with an arm of the bandit, generating stochastic rewards following an unk
Externí odkaz:
http://arxiv.org/abs/2305.00528
We consider the online caching problem for a cache of limited size. In a time-slotted system, a user requests one file from a large catalog in each slot. If the requested file is cached, the policy receives a unit reward and zero rewards otherwise. W
Externí odkaz:
http://arxiv.org/abs/2211.16051
We consider a constrained, pure exploration, stochastic multi-armed bandit formulation under a fixed budget. Each arm is associated with an unknown, possibly multi-dimensional distribution and is described by multiple attributes that are a function o
Externí odkaz:
http://arxiv.org/abs/2211.14768