Beyond dichotomies in reinforcement learning.

Beyond dichotomies in reinforcement learning.
复制标题

DOI:
10.1038/s41583-020-0355-6
复制
发表时间:
2020-10
期刊:
Nature reviews. Neuroscience
影响因子:
--
通讯作者:
Cockburn J
Cockburn J
中科院分区:
其他
文献类型:
--
作者:
Collins AGE;Cockburn J

文献摘要

参考文献

被引文献

相似文献

强化学习(RL)是一个对心理学、神经科学和机器学习特别重要的框架。这些领域之间的相互作用,通过RL的共同中心促进,促进了在单一框架内(例如多巴胺功能)进行多层次分析的范式转变。最近,更复杂的强化学习算法已经被纳入到更好地解释人类学习,特别是它对两个可分离系统的依赖。然而,除了许多好处之外,这种二分法也会扭曲问题,并可能导致对学习和决策的不必要的狭隘看法。在这里,我们概述了一些来自过于自信的映射算法的后果,例如基于模型的RL与无模型的RL,以及假定的认知过程。我们认为,该领域有能力超越简单的二分法,我们提出了一种方法,将研究问题重新聚焦于包括学习和决策的丰富而复杂的组成部分。
Reinforcement learning (RL) is a framework of particular importance to psychology, neuroscience, and machine learning. Interactions between these fields, as promoted through the common hub of RL, has facilitated paradigm shifts relating multiple levels of analysis within a singular framework (e.g dopamine function). Recently, more sophisticated RL algorithms have been incorporated to better account for human learning, and in particular its oft documented reliance on two separable systems. However, along with many benefits, this dichotomous lens can distort questions, and may contribute to an unnecessarily narrow perspective on learning and decision making. Here we outline some of the consequences that come from over-confidently mapping algorithms, such as model-based vs. model-free RL, with putative cognitive processes. We argue that the field is well positioned to move beyond simplistic dichotomies, and we propose a means of re-focusing research questions toward the rich and complex components that comprise learning and decision making.
推理,学习和创造力:额叶功能和人类决策。
DOI: 10.1371/journal.pbio.1001293
发表时间: 2012
期刊: PLoS biology
影响因子: 9.8
作者:
Collins A;Koechlin E
通讯作者: Koechlin E
工作记忆,强化学习和基于价值选择的努力之间的相互作用:精神分裂症的新范式和选择性缺陷。
DOI: 10.1016/j.biopsych.2017.05.017
发表时间: 2017-09-15
影响因子: 10.6
作者:
Collins AGE;Albrecht MA;Waltz JA;Gold JM;Frank MJ
通讯作者: Frank MJ
DOI: 10.1016/j.cognition.2008.08.011
发表时间: 2009-12
期刊: Cognition
影响因子: 3.4
作者:
Botvinick MM;Niv Y;Barto AG
通讯作者: Barto AG
DOI: 10.1037/abn0000259
发表时间: 2017-07
影响因子: 4.6
作者:
Barch DM;Carter CS;Gold JM;Johnson SL;Kring AM;MacDonald AW;Pizzagalli DA;Ragland JD;Silverstein SM;Strauss ME
通讯作者: Strauss ME
DOI: 10.1371/journal.pcbi.1004648
发表时间: 2015-12
影响因子: 4.3
作者:
Akam T;Costa R;Dayan P
通讯作者: Dayan P