Skip to main content
SpringerLink
Log in

The MaRz Algorithm: Towards an Artificial General Episodic Learner

  • Conference paper
  • First Online:
Artificial General Intelligence (AGI 2017)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10414))

Included in the following conference series:

  • 1707 Accesses

Abstract

An artificial general intelligence must be able to record and leverage its experiences to improve its behavior. In this paper, we present a novel, general, episodic learning algorithm that can operate effectively in an environment where its episodic memories are the only resource it has available for learning.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 44.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 59.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Anderson, J.R.: Cognitive Psychology and Its Implications. Worth Publishers, New York (2000)

    Google Scholar 

  2. Brom, C., Lukavský, J., Kadlec, R.: Episodic memory for human-like agents and human-like agents for episodic memory. Int. J. Mach. Conscious. 2(2) (2010)

    Google Scholar 

  3. Crook, P., Hayes, G.: Learning in a state of confusion: perceptual aliasing in grid world navigation. Towards Intel. Mob. Robots 4 (2003)

    Google Scholar 

  4. Faltersack, Z., Burns, B., Nuxoll, A., Crenshaw, T.L.: Ziggurat: steps toward a general episodic memory. In: AAAI Fall Symposium: Advances in Cognitive Systems (2011)

    Google Scholar 

  5. Gureckis, T.M., Love, B.C.: Short-term gains, long-term pains: how cues about state aid learning in dynamic environments. Cognition 113(3), 293–313 (2009)

    Article  Google Scholar 

  6. Ho, W.C., Dautenhahn, K., Nehaniv, C.L.: Computational memory architectures for autobiographic agents interacting in a complex virtual environment: a working model. Connection Sci. 20(1), 21–65 (2008)

    Article  Google Scholar 

  7. Hopcroft, J.E., Motwani, R., Ullman, J.D.: Automata Theory, Languages, and Computation. Pearson, Boston (2006)

    MATH  Google Scholar 

  8. Laird, J.E.: The Soar Cognitive Architecture. MIT Press, Cambridge (2012)

    Google Scholar 

  9. Lee, D., Yannakakis, M.: Testing finite-state machines: state identification and verification. IEEE Trans. Comput. 43(3), 306–320 (1994)

    Article  MathSciNet  Google Scholar 

  10. Li, J., Laird, J.E.: Spontaneous retrieval from long-term memory for a cognitive architecture. AAAI 2015, 544–550 (2015)

    Google Scholar 

  11. Loch, J., Singh, S.P.: Using eligibility traces to find the best memoryless policy in partially observable Markov decision processes. In: ICML 1998, pp. 323–331 (1998)

    Google Scholar 

  12. McCallum, R.A., Tesauro, G., Touretzky, D., Leen, T.: Instance-based state identification for reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 377–384 (1995)

    Google Scholar 

  13. Menager, D., Choi, D.: A robust implementation of episodic memory for a cognitive architecture. In: Proceedings of Annual Meeting of the Cognitive Science Society (2016)

    Google Scholar 

  14. Moore, E.F.: Gedanken-experiments on sequential machines. Automata Stud. 34, 129–153 (1956)

    MathSciNet  Google Scholar 

  15. Nuxoll, A., Tecuci, D., Ho, W.C., Wang, N.: Comparing forgetting algorithms for artificial episodic memory systems. In: Proceedings of the Symposium on Human Memory for Artificial Agents, AISB 2010, pp. 14–20 (2010)

    Google Scholar 

  16. Nuxoll, A.M., Laird, J.E.: Extending cognitive architecture with episodic memory. In: Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence. AAAI Press, Vancouver (2007)

    Google Scholar 

  17. Nuxoll, A.M., Laird, J.E.: Enhancing intelligent agents with episodic memory. Cogn. Syst. Res. 17, 34–48 (2012)

    Article  Google Scholar 

  18. Ram, A., Santamaria, J.C.: Continuous case-based reasoning. Artif. Intel. 90(1), 25–77 (1997)

    Article  MATH  Google Scholar 

  19. Russell, S.J.: Efficient memory-bounded search methods. In: ECAI 1992, vol. 92, pp. 1–5 (1992)

    Google Scholar 

  20. Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manage. 24(5), 513–523 (1988)

    Article  Google Scholar 

  21. Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT press, Cambridge (1998)

    Google Scholar 

  22. Tecuci, D., Porter, B.: A generic memory module for events. In: Proceedings of the 20th Florida Artificial Intelligence Research Society Conference (FLAIRS), Key West, FL (2007)

    Google Scholar 

  23. Tulving, E.: Elements of Episodic Memory. Clarendon Press, Oxford (1983)

    Google Scholar 

  24. Vanderwerf, E., Stiles, R., Warlen, A., Seibert, A., Bastien, K., Meyer, A., Nuxoll, A., Wallace, S.: Hash Functions for Episodic Recognition and Retrieval. In: Proceedings of the 29th Florida Artificial Intelligence Research Society Conference (FLAIRS), Key West, FL (2016)

    Google Scholar 

  25. Walker, B., Dalen, D., Faltersack, Z., Nuxoll, A.: Extracting episodic memory feature relevance without domain knowledge. In: Biologically Inspired Cognitive Architectures (BICA), pp. 431–437 (2011)

    Google Scholar 

  26. Whitehead, S.D., Ballard, D.H.: Learning to perceive and act by trial and error. Mach. Learn. 7(1), 45–83 (1991)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of Portland, Portland, OR, 97203, USA

    Christian Rodriguez, Giselle Marston, William Goolkasian, Ashley Rosenberg & Andrew Nuxoll

Authors
  1. Christian Rodriguez
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Giselle Marston
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. William Goolkasian
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ashley Rosenberg
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Andrew Nuxoll
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andrew Nuxoll .

Editor information

Editors and Affiliations

  1. Australian National University , Canberra, Aust Capital Terr, Australia

    Tom Everitt

  2. OpenCog Foundation , Hong Kong, China

    Ben Goertzel

  3. St. Petersburg State University , St. Petersburg, Russia

    Alexey Potapov

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Rodriguez, C., Marston, G., Goolkasian, W., Rosenberg, A., Nuxoll, A. (2017). The MaRz Algorithm: Towards an Artificial General Episodic Learner. In: Everitt, T., Goertzel, B., Potapov, A. (eds) Artificial General Intelligence. AGI 2017. Lecture Notes in Computer Science(), vol 10414. Springer, Cham. https://doi.org/10.1007/978-3-319-63703-7_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-63703-7_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-63702-0

  • Online ISBN: 978-3-319-63703-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation