arXiv cs.AI· Moto Shinriki, Yu Kono, Tatsuji Takahashi·· 12 小时前AI 评分20
将满足性重写为竞争性贝叶斯加权：未达成目标下目标导向选择的最小模型
Satisficing as competitive Bayesian weighting: a minimal model of goal-directed choice under an unattained target
AI 导读
研究者将风险敏感满足性（RS）这一 bandit 学习规则重写为类贝叶斯估计器 Attention Competitive Bayes（ACB），其中抱负水平作为每个动作的先验均值，有限试验预算决定证据能多强地覆盖它。ACB 由此产生“伪遗忘”现象：不再被采样的动作估计会向抱负水平松弛，而非依赖显式遗忘率。在 Bernoulli bandit 模拟中，依据证据调整抱负水平降低了 regret。
正文 · 原文
Abstract:Animals and humans often do not maximize; they act relative to goals (aspiration levels) that are frequently not yet met. How can a goal that is not (yet) realized organize choice? Deacon (2012) calls such absence-referenced organization \emph{ententional}, and García-Valdecasas and Deacon (2024) argue that ends are best understood as constraints rather than as particular states. We examine this idea in a minimal formal setting: Risk-sensitive Satisficing (RS), a bandit learning rule that values each action by its share of past trials multiplied by its surplus or shortfall relative to an aspiration level. We show that RS can be rewritten as a Bayesian-like estimator, Attention Competitive Bayes (ACB), in which the aspiration level is the prior mean of every action and the finite budget of trials sets how strongly evidence can override it. Two consequences follow. First, actions that are no longer sampled are partially overridden by the goal rather than by past observations: their estimates relax toward the aspiration level without any data being discarded. This ``pseudo-forgetting'' distinguishes ACB from models with an explicit forgetting rate. Second, when the aspiration is unattainable, exploration does not settle; in Bernoulli bandit simulations, adjusting the aspiration level from evidence reduced regret (expected loss). ACB offers an analyzable model in which an unattained goal and a limited attentional resource jointly constrain behavior, and it yields testable predictions about how organisms revalue options they have abandoned.
| Comments: | 15 pages, 4 figures, 2 tables, 1 algorithm |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML) |
| Cite as: | arXiv:2611.07270 [cs.LG] |
| (or arXiv:2611.07270v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07270 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tatsuji Takahashi [view email]
[v1]
Thu, 5 Nov 2026 00:45:40 UTC (1,307 KB)
来源：arXiv cs.AI · arxiv.org