Metraipolis › archive › dc_bb57989d1a30
Satisficing as competitive Bayesian weighting: a minimal model of goal-directed choice under an unattained target — arXiv:2611.07270
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07270
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:42:17.517Z
- SHA-256 of the archived text
5722cabfe40084467f9799edd704578d01ef08e5ed7325009b430c5718299528- Stable URL of this page
https://metraipolis.com/documento/dc_bb57989d1a30
How to cite
Satisficing as competitive Bayesian weighting: a minimal model of goal-directed choice under an unattained target — arXiv:2611.07270 — arXiv (en), https://arxiv.org/abs/2611.07270 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb57989d1a30 (Metraipolis archive dc_bb57989d1a30, sha256 5722cabfe40084467f9799edd704578d01ef08e5ed7325009b430c5718299528)
BibTeX
@misc{dcbb57989d1a30,
title = {Satisficing as competitive Bayesian weighting: a minimal model of goal-directed choice under an unattained target — arXiv:2611.07270},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07270},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb57989d1a30; sha256 5722cabfe40084467f9799edd704578d01ef08e5ed7325009b430c5718299528},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07270. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.07270 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:18:42.671Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).