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:
影响因子:
--
通讯作者:
Cockburn J
中科院分区:
文献类型:
--
作者:
Collins AGE;Cockburn J
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.
登录
查看更多内容
影响因子:
9.8
作者:
Collins A;Koechlin E
通讯作者:
Koechlin E
影响因子:
10.6
作者:
Collins AGE;Albrecht MA;Waltz JA;Gold JM;Frank MJ
通讯作者:
Frank MJ
影响因子:
3.4
作者:
Botvinick MM;Niv Y;Barto AG
通讯作者:
Barto AG
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
影响因子:
4.3
作者:
Akam T;Costa R;Dayan P
通讯作者:
Dayan P