Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951063049> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2951063049 abstract "The model of a non-Bayesian agent who faces a repeated game with incomplete information against Nature is an appropriate tool for modeling general agent-environment interactions. In such a model the environment state (controlled by Nature) may change arbitrarily, and the feedback/reward function is initially unknown. The agent is not Bayesian, that is he does not form a prior probability neither on the state selection strategy of Nature, nor on his reward function. A policy for the agent is a function which assigns an action to every history of observations and actions. Two basic feedback structures are considered. In one of them -- the perfect monitoring case -- the agent is able to observe the previous environment state as part of his feedback, while in the other -- the imperfect monitoring case -- all that is available to the agent is the reward obtained. Both of these settings refer to partially observable processes, where the current environment state is unknown. Our main result refers to the competitive ratio criterion in the perfect monitoring case. We prove the existence of an efficient stochastic policy that ensures that the competitive ratio is obtained at almost all stages with an arbitrarily high probability, where efficiency is measured in terms of rate of convergence. It is further shown that such an optimal policy does not exist in the imperfect monitoring case. Moreover, it is proved that in the perfect monitoring case there does not exist a deterministic policy that satisfies our long run optimality criterion. In addition, we discuss the maxmin criterion and prove that a deterministic efficient optimal strategy does exist in the imperfect monitoring case under this criterion. Finally we show that our approach to long-run optimality can be viewed as qualitative, which distinguishes it from previous work in this area." @default.
- W2951063049 created "2019-06-27" @default.
- W2951063049 creator A5003520806 @default.
- W2951063049 creator A5064301538 @default.
- W2951063049 date "1997-10-31" @default.
- W2951063049 modified "2023-10-16" @default.
- W2951063049 title "Dynamic Non-Bayesian Decision Making" @default.
- W2951063049 cites W1979865129 @default.
- W2951063049 doi "https://doi.org/10.48550/arxiv.cs/9711104" @default.
- W2951063049 hasPublicationYear "1997" @default.
- W2951063049 type Work @default.
- W2951063049 sameAs 2951063049 @default.
- W2951063049 citedByCount "0" @default.
- W2951063049 crossrefType "posted-content" @default.
- W2951063049 hasAuthorship W2951063049A5003520806 @default.
- W2951063049 hasAuthorship W2951063049A5064301538 @default.
- W2951063049 hasBestOaLocation W29510630491 @default.
- W2951063049 hasConcept C107673813 @default.
- W2951063049 hasConcept C11413529 @default.
- W2951063049 hasConcept C123676819 @default.
- W2951063049 hasConcept C126255220 @default.
- W2951063049 hasConcept C138885662 @default.
- W2951063049 hasConcept C14036430 @default.
- W2951063049 hasConcept C144237770 @default.
- W2951063049 hasConcept C154945302 @default.
- W2951063049 hasConcept C162324750 @default.
- W2951063049 hasConcept C177142836 @default.
- W2951063049 hasConcept C200594392 @default.
- W2951063049 hasConcept C2777303404 @default.
- W2951063049 hasConcept C2780310539 @default.
- W2951063049 hasConcept C33923547 @default.
- W2951063049 hasConcept C41008148 @default.
- W2951063049 hasConcept C41895202 @default.
- W2951063049 hasConcept C48103436 @default.
- W2951063049 hasConcept C50522688 @default.
- W2951063049 hasConcept C73795354 @default.
- W2951063049 hasConcept C78458016 @default.
- W2951063049 hasConcept C81917197 @default.
- W2951063049 hasConcept C86803240 @default.
- W2951063049 hasConceptScore W2951063049C107673813 @default.
- W2951063049 hasConceptScore W2951063049C11413529 @default.
- W2951063049 hasConceptScore W2951063049C123676819 @default.
- W2951063049 hasConceptScore W2951063049C126255220 @default.
- W2951063049 hasConceptScore W2951063049C138885662 @default.
- W2951063049 hasConceptScore W2951063049C14036430 @default.
- W2951063049 hasConceptScore W2951063049C144237770 @default.
- W2951063049 hasConceptScore W2951063049C154945302 @default.
- W2951063049 hasConceptScore W2951063049C162324750 @default.
- W2951063049 hasConceptScore W2951063049C177142836 @default.
- W2951063049 hasConceptScore W2951063049C200594392 @default.
- W2951063049 hasConceptScore W2951063049C2777303404 @default.
- W2951063049 hasConceptScore W2951063049C2780310539 @default.
- W2951063049 hasConceptScore W2951063049C33923547 @default.
- W2951063049 hasConceptScore W2951063049C41008148 @default.
- W2951063049 hasConceptScore W2951063049C41895202 @default.
- W2951063049 hasConceptScore W2951063049C48103436 @default.
- W2951063049 hasConceptScore W2951063049C50522688 @default.
- W2951063049 hasConceptScore W2951063049C73795354 @default.
- W2951063049 hasConceptScore W2951063049C78458016 @default.
- W2951063049 hasConceptScore W2951063049C81917197 @default.
- W2951063049 hasConceptScore W2951063049C86803240 @default.
- W2951063049 hasLocation W29510630491 @default.
- W2951063049 hasLocation W29510630492 @default.
- W2951063049 hasOpenAccess W2951063049 @default.
- W2951063049 hasPrimaryLocation W29510630491 @default.
- W2951063049 hasRelatedWork W1496801567 @default.
- W2951063049 hasRelatedWork W2004230228 @default.
- W2951063049 hasRelatedWork W2113798763 @default.
- W2951063049 hasRelatedWork W2145796981 @default.
- W2951063049 hasRelatedWork W2360321812 @default.
- W2951063049 hasRelatedWork W2395295193 @default.
- W2951063049 hasRelatedWork W2610227658 @default.
- W2951063049 hasRelatedWork W2900431508 @default.
- W2951063049 hasRelatedWork W3088364074 @default.
- W2951063049 hasRelatedWork W3122057932 @default.
- W2951063049 isParatext "false" @default.
- W2951063049 isRetracted "false" @default.
- W2951063049 magId "2951063049" @default.
- W2951063049 workType "article" @default.