Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951862331> ?p ?o ?g. }
- W2951862331 abstract "We present a formal model of human decision-making in explore-exploit tasks using the context of multi-armed bandit problems, where the decision-maker must choose among multiple options with uncertain rewards. We address the standard multi-armed bandit problem, the multi-armed bandit problem with transition costs, and the multi-armed bandit problem on graphs. We focus on the case of Gaussian rewards in a setting where the decision-maker uses Bayesian inference to estimate the reward values. We model the decision-maker's prior knowledge with the Bayesian prior on the mean reward. We develop the upper credible limit (UCL) algorithm for the standard multi-armed bandit problem and show that this deterministic algorithm achieves logarithmic cumulative expected regret, which is optimal performance for uninformative priors. We show how good priors and good assumptions on the correlation structure among arms can greatly enhance decision-making performance, even over short time horizons. We extend to the stochastic UCL algorithm and draw several connections to human decision-making behavior. We present empirical data from human experiments and show that human performance is efficiently captured by the stochastic UCL algorithm with appropriate parameters. For the multi-armed bandit problem with transition costs and the multi-armed bandit problem on graphs, we generalize the UCL algorithm to the block UCL algorithm and the graphical block UCL algorithm, respectively. We show that these algorithms also achieve logarithmic cumulative expected regret and require a sub-logarithmic expected number of transitions among arms. We further illustrate the performance of these algorithms with numerical examples. NB: Appendix G included in this version details minor modifications that correct for an oversight in the previously-published proofs. The remainder of the text reflects the published work." @default.
- W2951862331 created "2019-06-27" @default.
- W2951862331 creator A5032304399 @default.
- W2951862331 creator A5052107131 @default.
- W2951862331 creator A5085821818 @default.
- W2951862331 date "2013-07-23" @default.
- W2951862331 modified "2023-09-27" @default.
- W2951862331 title "Modeling Human Decision-making in Generalized Gaussian Multi-armed Bandits" @default.
- W2951862331 cites W104909430 @default.
- W2951862331 cites W105998487 @default.
- W2951862331 cites W1486950299 @default.
- W2951862331 cites W1501823362 @default.
- W2951862331 cites W1591803298 @default.
- W2951862331 cites W1907688256 @default.
- W2951862331 cites W1944301273 @default.
- W2951862331 cites W1965392255 @default.
- W2951862331 cites W1965819279 @default.
- W2951862331 cites W1970966707 @default.
- W2951862331 cites W1978837788 @default.
- W2951862331 cites W1980560560 @default.
- W2951862331 cites W1998498767 @default.
- W2951862331 cites W2000080679 @default.
- W2951862331 cites W2008098735 @default.
- W2951862331 cites W2011024242 @default.
- W2951862331 cites W2012647368 @default.
- W2951862331 cites W2015153742 @default.
- W2951862331 cites W2021622496 @default.
- W2951862331 cites W2023599408 @default.
- W2951862331 cites W2024060531 @default.
- W2951862331 cites W2025800439 @default.
- W2951862331 cites W2030160111 @default.
- W2951862331 cites W2039522160 @default.
- W2951862331 cites W2048524268 @default.
- W2951862331 cites W2049934117 @default.
- W2951862331 cites W2058414536 @default.
- W2951862331 cites W2078394884 @default.
- W2951862331 cites W2097931172 @default.
- W2951862331 cites W2107726111 @default.
- W2951862331 cites W2121863487 @default.
- W2951862331 cites W2134243390 @default.
- W2951862331 cites W2138728841 @default.
- W2951862331 cites W2139622428 @default.
- W2951862331 cites W2141708418 @default.
- W2951862331 cites W2142971854 @default.
- W2951862331 cites W2152161277 @default.
- W2951862331 cites W2156107305 @default.
- W2951862331 cites W2165607537 @default.
- W2951862331 cites W2166566250 @default.
- W2951862331 cites W2168405694 @default.
- W2951862331 cites W2168709337 @default.
- W2951862331 cites W2317700292 @default.
- W2951862331 cites W2341171179 @default.
- W2951862331 cites W2397611513 @default.
- W2951862331 cites W2914275007 @default.
- W2951862331 cites W3125634603 @default.
- W2951862331 hasPublicationYear "2013" @default.
- W2951862331 type Work @default.
- W2951862331 sameAs 2951862331 @default.
- W2951862331 citedByCount "2" @default.
- W2951862331 countsByYear W29518623312013 @default.
- W2951862331 countsByYear W29518623312016 @default.
- W2951862331 crossrefType "posted-content" @default.
- W2951862331 hasAuthorship W2951862331A5032304399 @default.
- W2951862331 hasAuthorship W2951862331A5052107131 @default.
- W2951862331 hasAuthorship W2951862331A5085821818 @default.
- W2951862331 hasConcept C107673813 @default.
- W2951862331 hasConcept C119857082 @default.
- W2951862331 hasConcept C121332964 @default.
- W2951862331 hasConcept C123197309 @default.
- W2951862331 hasConcept C126255220 @default.
- W2951862331 hasConcept C134306372 @default.
- W2951862331 hasConcept C150325174 @default.
- W2951862331 hasConcept C154945302 @default.
- W2951862331 hasConcept C163716315 @default.
- W2951862331 hasConcept C177769412 @default.
- W2951862331 hasConcept C33923547 @default.
- W2951862331 hasConcept C39927690 @default.
- W2951862331 hasConcept C41008148 @default.
- W2951862331 hasConcept C50817715 @default.
- W2951862331 hasConcept C62520636 @default.
- W2951862331 hasConcept C73602740 @default.
- W2951862331 hasConcept C84525736 @default.
- W2951862331 hasConceptScore W2951862331C107673813 @default.
- W2951862331 hasConceptScore W2951862331C119857082 @default.
- W2951862331 hasConceptScore W2951862331C121332964 @default.
- W2951862331 hasConceptScore W2951862331C123197309 @default.
- W2951862331 hasConceptScore W2951862331C126255220 @default.
- W2951862331 hasConceptScore W2951862331C134306372 @default.
- W2951862331 hasConceptScore W2951862331C150325174 @default.
- W2951862331 hasConceptScore W2951862331C154945302 @default.
- W2951862331 hasConceptScore W2951862331C163716315 @default.
- W2951862331 hasConceptScore W2951862331C177769412 @default.
- W2951862331 hasConceptScore W2951862331C33923547 @default.
- W2951862331 hasConceptScore W2951862331C39927690 @default.
- W2951862331 hasConceptScore W2951862331C41008148 @default.
- W2951862331 hasConceptScore W2951862331C50817715 @default.
- W2951862331 hasConceptScore W2951862331C62520636 @default.
- W2951862331 hasConceptScore W2951862331C73602740 @default.
- W2951862331 hasConceptScore W2951862331C84525736 @default.
- W2951862331 hasLocation W29518623311 @default.