Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989852012> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W2989852012 endingPage "44" @default.
- W2989852012 startingPage "31" @default.
- W2989852012 abstract "Companies like Google and Microsoft run billions of auctions every day to sell advertising opportunities. Any change to the rules of these auctions can have a tremendous effect on the revenue of the company and the welfare of the advertisers and the users. Therefore, any change requires careful evaluation of its potential impacts. Currently, such impacts are often evaluated by running simulations or small controlled experiments. This, however, misses the important factor that the advertisers respond to changes. Our goal is to build a theoretical framework for predicting the actions of an agent (the advertiser) that is optimizing her actions in an uncertain environment. We model this problem using a variant of the multi-armed bandit setting where playing an arm is costly. The cost of each arm changes over time and is publicly observable. The value of playing an arm is drawn stochastically from a static distribution and is observed by the agent and not by us. We, however, observe the actions of the agent. Our main result is that assuming the agent is playing a strategy with a regret of at most f(T) within the first T rounds, we can learn to play the multi-armed bandits game (without observing the rewards) in such a way that the regret of our selected actions is at most (O(k^4(f(T)+1)log (T))), where k is the number of arms." @default.
- W2989852012 created "2019-12-05" @default.
- W2989852012 creator A5018777906 @default.
- W2989852012 creator A5051013328 @default.
- W2989852012 creator A5078015285 @default.
- W2989852012 creator A5091439062 @default.
- W2989852012 date "2019-01-01" @default.
- W2989852012 modified "2023-09-29" @default.
- W2989852012 title "Response Prediction for Low-Regret Agents" @default.
- W2989852012 cites W1522968011 @default.
- W2989852012 cites W1975566260 @default.
- W2989852012 cites W2007331509 @default.
- W2989852012 cites W2011384577 @default.
- W2989852012 cites W2038701206 @default.
- W2989852012 cites W2051015143 @default.
- W2989852012 cites W2072459156 @default.
- W2989852012 cites W2078319130 @default.
- W2989852012 cites W2120416704 @default.
- W2989852012 cites W2122596677 @default.
- W2989852012 cites W2146096504 @default.
- W2989852012 cites W2147347406 @default.
- W2989852012 cites W2404673495 @default.
- W2989852012 cites W2950929549 @default.
- W2989852012 cites W2962979247 @default.
- W2989852012 cites W3123396550 @default.
- W2989852012 cites W4231144620 @default.
- W2989852012 doi "https://doi.org/10.1007/978-3-030-35389-6_3" @default.
- W2989852012 hasPublicationYear "2019" @default.
- W2989852012 type Work @default.
- W2989852012 sameAs 2989852012 @default.
- W2989852012 citedByCount "1" @default.
- W2989852012 countsByYear W29898520122022 @default.
- W2989852012 crossrefType "book-chapter" @default.
- W2989852012 hasAuthorship W2989852012A5018777906 @default.
- W2989852012 hasAuthorship W2989852012A5051013328 @default.
- W2989852012 hasAuthorship W2989852012A5078015285 @default.
- W2989852012 hasAuthorship W2989852012A5091439062 @default.
- W2989852012 hasBestOaLocation W29898520122 @default.
- W2989852012 hasConcept C119857082 @default.
- W2989852012 hasConcept C154945302 @default.
- W2989852012 hasConcept C41008148 @default.
- W2989852012 hasConcept C50817715 @default.
- W2989852012 hasConceptScore W2989852012C119857082 @default.
- W2989852012 hasConceptScore W2989852012C154945302 @default.
- W2989852012 hasConceptScore W2989852012C41008148 @default.
- W2989852012 hasConceptScore W2989852012C50817715 @default.
- W2989852012 hasLocation W29898520121 @default.
- W2989852012 hasLocation W29898520122 @default.
- W2989852012 hasOpenAccess W2989852012 @default.
- W2989852012 hasPrimaryLocation W29898520121 @default.
- W2989852012 hasRelatedWork W1947085858 @default.
- W2989852012 hasRelatedWork W2101991911 @default.
- W2989852012 hasRelatedWork W2155070487 @default.
- W2989852012 hasRelatedWork W2174986909 @default.
- W2989852012 hasRelatedWork W2527791220 @default.
- W2989852012 hasRelatedWork W2748952813 @default.
- W2989852012 hasRelatedWork W2899084033 @default.
- W2989852012 hasRelatedWork W3107474891 @default.
- W2989852012 hasRelatedWork W3123835761 @default.
- W2989852012 hasRelatedWork W4311589891 @default.
- W2989852012 isParatext "false" @default.
- W2989852012 isRetracted "false" @default.
- W2989852012 magId "2989852012" @default.
- W2989852012 workType "book-chapter" @default.