Abstract
Episodic memory in cognitive architectures allows intelligent agents to query their past experiences to influence decision making. Episodic memory in the Soar cognitive architecture must efficiently encode, store, search and reconstruct episodes as snapshots of short term working memory. The performance of the current search algorithm can be improved by doing a structural match phase first on all stored data and enforcing arc consistency in the first stage of the structural match. We demonstrate experimentally the performance of the improved search algorithm in two Soar environments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Original version available: http://gabrielecirulli.github.io/2048/.
References
Dechter, R.: Constraint Processing. Morgan Kaufmann, San Francisco (2003)
Derbinsky, N., Laird, J.E.: Efficiently implementing episodic memory. In: McGinty, L., Wilson, D.C. (eds.) ICCBR 2009. LNCS, vol. 5650, pp. 403–417. Springer, Heidelberg (2009)
Derbinsky, N.L.: Effective and efficient memory for generally intelligent agents. Ph.D. thesis, The University of Michigan (2012)
Laird, J.E.: Extending the soar cognitive architecture. Front. Artif. Intell. Appl. 171, 224 (2008)
Laird, J.E.: The Soar Cognitive Architecture. The MIT Press, Cambridge (2012)
Li, F.: epmemcsp (2015). https://github.com/fli/epmemcsp
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Li, F., Frost, J., Phillips, B.J. (2015). An Episodic Memory Retrieval Algorithm for the Soar Cognitive Architecture. In: Pfahringer, B., Renz, J. (eds) AI 2015: Advances in Artificial Intelligence. AI 2015. Lecture Notes in Computer Science(), vol 9457. Springer, Cham. https://doi.org/10.1007/978-3-319-26350-2_30
Download citation
DOI: https://doi.org/10.1007/978-3-319-26350-2_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26349-6
Online ISBN: 978-3-319-26350-2
eBook Packages: Computer ScienceComputer Science (R0)