Analyzing Human Search Behavior When Subjective Returns are Unobservable

Analyzing Human Search Behavior When Subjective Returns are Unobservable
复制标题

当主观回报不可观察时分析人类搜索行为

DOI:
10.1007/s10614-023-10388-1
复制
发表时间:
2023
影响因子:
2
通讯作者:
Tetsuya Shimokawa
Tetsuya Shimokawa
中科院分区:
经济学4区
文献类型:
--
作者:
Shinji Nakazato;Bojian Yang;Tetsuya Shimokawa

文献摘要

参考文献

相似文献

探索与开发困境是人类信息获取和顺序信念形成过程中的一个关键问题,多武装强盗问题被广泛用于解决这一问题。结合SoftMax型概率选择、高斯过程回归型信念更新和上置信区间型评价的SGU模型由于具有较高的描述精度而备受关注。然而,这个模型假设分析人员可以获得人们选择的回报,但是在许多现实任务中,这个假设不能成立,因为只有选择是可观察的。此外,许多回报都是主观的。作者介绍了一种新的模型拟合方法,克服了这一障碍,并使用来自基于智能体的模拟和真实消费者数据的数据集来评估其性能。这种方法有可能大大扩大SGU模型可以应用的问题范围。
The exploration versus exploitation dilemma is a critical issue in human information acquisition and sequential belief formation, and the multi-armed bandit problem has been widely used to address it. Because of its high descriptive accuracy, the SGU model, which combines SoftMax type probabilistic selection, Gaussian process regression type belief updating, and upper confidence interval type evaluation, has attracted much attention. However, this model assumes that the analyst has access to the returns from people’s choices, but in many realistic tasks, this assumption cannot be made because only choices are observable. Moreover, many of the returns are subjective. The authors introduce a new model-fitting method that overcomes this barrier and evaluates its performance using data sets derived from agent-based simulations and real consumer data. This approach has the potential to significantly broaden the range of issues to which the SGU model can be applied.
DOI: 10.1146/annurev-psych-122414-033625
发表时间: 2017-01-03
影响因子: 24.8
作者:
Gershman SJ;Daw ND
通讯作者: Daw ND
不确定性与探索
DOI: 10.1101/265504
发表时间: 2018
期刊: bioRxiv
影响因子: --
作者:
S. Gershman
通讯作者: S. Gershman
顺序分配问题的最优自适应策略
DOI: --
发表时间: 1996
期刊:
影响因子: --
作者:
A. Burnetas;M. Katehakis
通讯作者: M. Katehakis
泛化指导人类在广阔的决策空间中进行探索
DOI: --
发表时间: 2017
影响因子: 29.9
作者:
Charley M. Wu;Eric Schulz;M. Speekenbrink;Jonathan D. Nelson;Björn Meder
通讯作者: Björn Meder