logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Action chunking as conditional policy compression

delete2025-07-01
delete0
PRE
AI
L
Lucy Lai
A
Ann Zixiang Huang
S
Samuel J. Gershman
DOI：10.1016/j.cognition.2025.106201delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Action chunking emerges as a trade-off between reward and cognitive effort. • People use temporal structure to reduce policy complexity and respond faster. • Higher working memory load leads to more chunking to conserve cognitive resources. • Chunking frees up memory for other, unchunked information.
Keywords:
action chunking
cognitive effort
temporal structure
working memory
policy complexity

Journal

Cognition cover
Cognition
IF:
2.8
Papers:
544
Citations:
2.1W

Organization

H
Harvard University
Scholars:
26.5W
Papers: 22.0W
Citations: 28.7W
Cited Papers

Cited Papers

No cited papers available