Results for the “Keep or Donate” problem.

(a) Fraction of Donate actions for each type of agent, averaged over 100 episodes, each lasting 100 time steps. (b) Cumulative sum of Donate (+1) and Keep (–1) actions over the timecourse of an episode, averaged over 100 episodes (error bars show 1 stan...

وصف كامل

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Nigini Oliveira (10284854) (author)
مؤلفون آخرون:	Jasmine Li (4424320) (author), Koosha Khalvati (10284857) (author), Rodolfo Cortes Barragan (22813448) (author), Katharina Reinecke (10284863) (author), Andrew N. Meltzoff (8938331) (author), Rajesh P. N. Rao (6725039) (author)
منشور في:	2025
الموضوعات:	Neuroscience Physiology Cancer Science Policy Mental Health universal moral code two cultural groups time decision making altruistic characteristics reflective ai system operating particular culture learns div >< p agents ’ actions altruistic cultural values ai agent learning altruistic behavior ai agents group ’ values directly specific values different values attuned ai ai systems therefore argue social practices results provide open question implicitly </ implicit learning human subjects human cultures experimental paradigm culture based concept demonstration child raised average behavior artificial intelligence approach using
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

الوصف
الملخص:	<p><b>(a)</b> Fraction of Donate actions for each type of agent, averaged over 100 episodes, each lasting 100 time steps. <b>(b)</b> Cumulative sum of Donate (+1) and Keep (–1) actions over the timecourse of an episode, averaged over 100 episodes (error bars show 1 standard deviation above/below mean). <b>(c)</b> Four example episodes showing the monetary balance and actions employed by each of the four trained AI agents.</p>

Results for the “Keep or Donate” problem.

مواد مشابهة