A cognitive satisficing strategy for bandit problems. Issue 2 (4th March 2017)

• Record Type: Journal Article
• Authors: Kohno, Yu; Takahashi, Tatsuji
• Is Part Of: International journal of parallel, emergent and distributed systems. Volume 32:Issue 2(2017)
• Page Start: 232
• Page End: 242
• Publication Date: 2017-03-04
• Subjects: Bounded rationality -- bounded optimality -- computational rationality -- UCB1 -- multi-armed bandit problems -- reinforcement learning; Parallel computers -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Computer algorithms -- Periodicals; 004.35
• DOI: 10.1080/17445760.2015.1075531
• Languages: English
• ISSNs: 1744-5760

Abstract

Abstract : When learning and test phases are not separated, there is a trade-off between speed and accuracy. This is a universal problem for agents acting under uncertainty. To address this trade-off, we employ a strategy called satisficing, which looks for actions that are satisfactory with respect to a given reference level. In this study, we introduce a satisficing value function, the loosely symmetric model with variable reference (LSVR) which is an extension of the loosely symmetric model inspired by some causal and perceptual human properties. We tested the performance of the LSVR in K -armed bandit problems that deal with the trade-off in the simplest possible way. Our results show that the LSVR enables effective online optimisation through satisficing.