Learning effects of robot actions using temporal associations

P. R. Cohen, C. Sutton, B. Burns

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Scopus citations

Abstract

Agents need to know the effects of their actions. Strong associations between actions and effects can be found by counting how often they co-occur. We present an algorithm that learns temporal patterns expressed as fluents, i.e. propositions with temporal extent. The fluent-learning algorithm is hierarchical and unsupervised. It works by maintaining co-occurrence statistics on pairs of fluents. In experiments on a mobile robot, the fluent-learning algorithm found temporal associations that correspond to effects of the robot's actions.

Original languageEnglish (US)
Title of host publicationProceedings - 2nd International Conference on Development and Learning, ICDL 2002
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages96-101
Number of pages6
ISBN (Electronic)0769514596, 9780769514598
DOIs
StatePublished - 2002
Event2nd International Conference on Development and Learning, ICDL 2002 - Cambridge, United States
Duration: Jun 12 2002Jun 15 2002

Publication series

NameProceedings - 2nd International Conference on Development and Learning, ICDL 2002

Other

Other2nd International Conference on Development and Learning, ICDL 2002
CountryUnited States
CityCambridge
Period6/12/026/15/02

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Learning effects of robot actions using temporal associations'. Together they form a unique fingerprint.

Cite this