Call for Paper - February 2021 Edition
IJCA solicits original research papers for the February 2021 Edition. Last date of manuscript submission is January 20, 2021. Read More

How Soar Agent Learns: Episodic Memory

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2019
Authors:
Nitin Bansal, S. Srinivasan
10.5120/ijca2019918328

Nitin Bansal and S Srinivasan. How Soar Agent Learns: Episodic Memory. International Journal of Computer Applications 181(36):21-25, January 2019. BibTeX

@article{10.5120/ijca2019918328,
	author = {Nitin Bansal and S. Srinivasan},
	title = {How Soar Agent Learns: Episodic Memory},
	journal = {International Journal of Computer Applications},
	issue_date = {January 2019},
	volume = {181},
	number = {36},
	month = {Jan},
	year = {2019},
	issn = {0975-8887},
	pages = {21-25},
	numpages = {5},
	url = {http://www.ijcaonline.org/archives/volume181/number36/30267-2019918328},
	doi = {10.5120/ijca2019918328},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

The main objective of this paper is to make the agent learn from its experiences in order to improve its intelligence. Learning is performed with the help of episodic memory which store the previous experiences in the form of episodes in order to solve the problem. With the help of the implementation in soar of an example, this paper presents the improvement in intelligence. In this paper episodes (previous experiences) which are in the form of WME (working memory elements) work to improve the intelligence. Objective of this paper is to show that learning always improves performance i.e. as agent learns more, the performance will improve.

References

  1. Laird, J. E, “The Soar Cognitive Architecture”,. MIT Press, Cambridge, MA, 20102.
  2. Bansal. N, Rajan. N., Srinivasan. S., March 30, 2013 , “Multi–Memory System: The Cognitive Architecture- SOAR”, NCACT-2013
  3. Andrew M. Nuxoll and John E. Laird, “Extending Cognitive Architecture with Episodic Memory”, University of Michigan, Ann Arbor, MI 48109-2121
  4. Derbinsky. N., “Efficiently Implementing Episodic Memory in Soar”, September 8, 2008.
  5. Laird, John & Newell, Allen & Rosenbloom, Paul, 1987, SOAR: An Architecture for General Intelligence. Artificial Intelligence. 33. 1-. 10.1016/0004-3702(87)90050-6..
  6. Endel Tulving, 2002, ” EPISODIC MEMORY: From Mind to Brain”, Annual Review of Psychology Vol. 53:1-25 .
  7. Adrian Horzyk  ; Janusz A. Starzyk ; James Graham , Dec. 2017 , ” Integration of Semantic and Episodic Memories”, IEEE Transactions on Neural Networks and Learning Systems,  Volume: 28 , Issue: 12 ,.
  8. Nuxoll, A., ”Enhancing Intelligent Agents with Episodic Memory”, PhD Dissertation, University of Michigan, 2007.
  9. Tulving, E., “Elements of Episodic Memory”, Oxford: Clarendon Press, 1983.
  10. Episodic memory available at “https://en.wikipedia.org/wiki/Episodic_memory”.
  11. “Introduction to the Soar Cognitive Architecture”, (PST 11), available at http://acs.ist.psu.edu/misc/nottingham/pst/hungry-thirsty/full.html 5/18, 2018.

Keywords

Soar, Working Memory, Episodic Memory, VisualSoar, epmem, Cues, Working Memory Elements.