Cogprints

Logic, self-awareness and self-improvement: The metacognitive loop and the problem of brittleness

Anderson, Dr. Michael L. and Perlis, Prof. Donald R. (2005) Logic, self-awareness and self-improvement: The metacognitive loop and the problem of brittleness. [Journal (Paginated)]

Full text available as:

[img]
Preview
PDF
196Kb

Abstract

This essay describes a general approach to building perturbation-tolerant autonomous systems, based on the conviction that artificial agents should be able notice when something is amiss, assess the anomaly, and guide a solution into place. We call this basic strategy of self-guided learning the metacognitive loop; it involves the system monitoring, reasoning about, and, when necessary, altering its own decision-making components. In this essay, we (a) argue that equipping agents with a metacognitive loop can help to overcome the brittleness problem, (b) detail the metacognitive loop and its relation to our ongoing work on time-sensitive commonsense reasoning, (c) describe specific, implemented systems whose perturbation tolerance was improved by adding a metacognitive loop, and (d) outline both short-term and long-term research agendas.

Item Type:Journal (Paginated)
Keywords:Metareasoning, time, non-monotonic reasoning, active logic, brittleness, autonomous agents
Subjects:Computer Science > Artificial Intelligence
ID Code:3950
Deposited By:Anderson, Dr. Michael
Deposited On:11 Feb 2005
Last Modified:11 Mar 2011 08:55

References in Article

Select the SEEK icon to attempt to find the referenced article. If it does not appear to be in cogprints you will be forwarded to the paracite service. Poorly formated references will probably not work.

James F. Allen and George Ferguson. Actions and Events in Interval Temporal Logic. Journal of Logic and Computation, 4(5), 1994.

James F. Allen, Bradford W. Miller, Eric K. Ringger, and Teresa Sikorski. A robust system for natural spoken dialogue. In Proceedings of the 1996 Annual Meeting of the Association for Computational Linguistics (ACL-96), pages 62--70, 1996.

Michael L. Anderson. Embodied cognition: A field guide. Artificial Intelligence, 149(1):91--130, 2003.

Michael L. Anderson, Walid Gomaa, John Grant, and Don Perlis. On the reasoning of real-word agents: Toward a semantics for active logic, in preparation.

Michael L. Anderson, Darsana Josyula, Yoshi Okamoto, and Don Perlis. Time-situated agency: Active Logic and intention formation. In Workshop on Cognitive Agents, 25th German Conference on Artificial Intelligence, 2002.

Michael L. Anderson, Darsana Josyula, and Don Perlis. Talking to computers. In Proceedings of the Workshop on Mixed Initiative Intelligent Systems, IJCAI-03, 2003.

Michael L. Anderson, Darsana Josyula, Don Perlis, and Khemdut Purang. Active logic for more effective human-computer interaction and other commonsense applications. In Proceedings of the Workshop Empirically Successful First-Order Reasoning, International Joint Conference on Automated Reasoning, 2004.

Michael L. Anderson, Tim Oates, Waiyian Chong, and Don Perlis. Enhancing reinforcement learning with metacognitive monitoring and control for improved perturbation tolerance, in preparation.

Michael L. Anderson, Yoshi Okamoto, Darsana Josyula, and Don Perlis. The use-mention distinction and its importance to HCI. In Proceedings of the Sixth Workshop on the Semantics and Pragmatics of Dialog, 2002.

Manjit Bhatia, Paul Chi, Waiyian Chong, Darsana P. Josyula, Michael Anderson, Yoshi Okamoto, Don Perlis, and K. Purang. Handling uncertainty with active logic. In Proceedings of the AAAI Fall Symposium on Uncertainty in Computation, 2001.

Wolfgang Bibel. Let's plan it deductively. Artificial Intelligence, 103(1-2):183--208, 1998.

Paul Bloom and Lori Markson. Capacities underlying word learning. Trends in Cognitive Scienes, 2(2):67--73, 1998.

R. A. Brooks. A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, RA-2:14--23, 1986.

R. A. Brooks. Intelligence without reason. In Proceedings of 12th Int. Joint Conf. on Artificial Intelligence, pages 569--95, 1991.

R. A. Brooks. From earwigs to humans. practice and future of autonomous agents. Robotics and Autonomous Systems, 20:291--304, 1997.

Rodney Brooks. Intelligence without representation. Artificial Intelligence, 47:139--60, 1991.

F. Brown, editor. The Frame Problem in Artificial Intelligence. Morgan Kaufmann, 1987.

Waiyian Chong, Michael O'Donovan-Anderson, Yoshi Okamoto, and Don Perlis. Seven days in the life of a robotic agent. In Proceedings of the GSFC/JPL Workshop on Radical Agent Concepts, 2002.

Jon Doyle. A Truth Maintenance System. Artificial Intelligence, 12(3):231--272, 1979.

Jon Doyle. A Model for Deliberation, Action, and Introspection. PhD thesis, Massachusetts Institute of Technology, 1980.

J. Elgot-Drapkin and D. Perlis. Reasoning situated in time I: Basic concepts. Journal of Experimental and Theoretical Artificial Intelligence, 2(1):75--98, 1990.

Dov M. Gabbay and John Woods. Agenda Relevance: A Study in Formal Pragmatics. North-Holland, 2003.

M. Ginsberg, editor. Readings in Nonmonotonic Reasoning. Morgan Kaufmann, 1987.

P. Gardenfors. Knowledge in Flux: Modeling the Dynamics of Epistemic States. MIT Press, Cambridge, MA, 1988.

Peter Gardenfors. Belief Revision. Cambridge University Press, Cambridge, 1992.

Peter Gardenfors and Hans Rott. Belief revision. In Dov M. Gabbay, Christopher J. Hogger, and John A. Robinson, editors, Handbook of Logic in Artificial Intelligence and Logic Programming, volume IV, pages 35--132. Oxford University Press, 1995.

Ken Hennacy, Nikil Swamy, and Don Perlis. RGL study in a hybrid real-time system. In Proceedings of the IASTED NCI, 2003.

Darsana Josyula, Michael L. Anderson, and Don Perlis. Towards domain-independent, task-oriented, conversational adequacy. In Proceedings of IJCAI-2003 Intelligent Systems Demonstrations, pages 1637--8, 2003.

H.H. Kendler and T.S. Kendler. Vertical and horizontal processes in problem solving. Psychological Review, 69:1--16, 1962.

H.H. Kendler and T.S. Kendler. Reversal-shift behavior: Some basic issues. Psychological Bulletin, 72:229--32, 1969.

Hesham Khalil. Logical Foundations of Default Reasoning. PhD thesis, University of Leipsig, Leipzig, Germany, 2002.

David Kirsh. Today the earwig, tomorrow man? Artificial Intelligence, 47(3):161--184, 1991.

G. F. Marcus. The Algebraic Mind: Integrating Connectionism and Cognitive Science . MIT Press, 2001.

J. McCarthy. Applications of circumscription to formalizing common-sense knowledge. Artificial Intelligence, 28(1):89--116, 1986.

J. McCarthy and P. Hayes. Some philosophical problems from the standpoint of artificial intelligence. In B. Meltzer and D. Michie, editors, Machine Intelligence, volume 4, pages 463--502. Edinburgh University Press, 1969.

O. Melnik and J.B. Pollack. Theory and scope of exact representation extraction from feed-forward networks. Cognitive Systems Research, 3(2), 2002.

M. Miller. A View of One's Past and Other Aspects of Reasoned Change in Belief. PhD thesis, Department of Computer Science, University of Maryland, College Park, Maryland, 1993.

M. Miller and D. Perlis. Presentations and this and that: logic in action. In Proceedings of the 15th Annual Conference of the Cognitive Science Society, Boulder, Colorado, 1993.

Andrew W. Moore and Christopher G. Atkeson. Prioritized sweeping: Reinforcement learning with less data and less time. Machine Learning, 13:103--130, 1993.

T. O. Nelson. Consciousness and metacognition. American Psychologist, 51:102--16, 1996.

T. O. Nelson and J. Dunlosky. Norms of paired-associate recall during multitrial learning of swahili-english translation equivalents. Memory, 2:325--35, 1994.

T. O. Nelson, J. Dunlosky, A. Graf, and L. Narens. Utilization of metacognitive judgments in the allocation of study during multitrial learning. Psychological Science, 4:207--13, 1994.

M. Nirkhe, S. Kraus, M. Miller, and D. Perlis. How to (plan to) meet a deadline between now and then. Journal of logic computation, 7(1):109--156, 1997.

D. Perlis. On the consistency of commonsense reasoning. Computational Intelligence, 2:180--190, 1986.

D. Perlis. Sources of, and exploiting, inconsistency: Preliminary report. Journal of APPLIED NON-CLASSICAL LOGICS, 7, 1997.

D. Perlis, K. Purang, and C. Andersen. Conversational adequacy: mistakes are the essence. Int. J. Human-Computer Studies, 48:553--575, 1998.

G. Priest. Paraconsistent logic. In D. Gabbay and F. Guenther, editors, Handbook of Philosophical Logic, 2ed, pages 287--393. Kluwer Academic Publishers, 2002.

G. Priest, R. Routley, and J. Norman. Paraconsistent Logic: Essays on the Inconsistent. Philosophia Verlag, München, 1989.

K. Purang. Systems that detect and repair their own mistakes. PhD thesis, Department of Computer Science, University of Maryland, College Park, Maryland, 2001.

K. Purang, D. Purushothaman, D. Traum, C. Andersen, D. Traum, and D. Perlis. Practical reasoning and plan execution with active logic. In Proceedings of the IJCAI'99 Workshop on Practical Reasoning and Rationality, 1999.

N. Rescher and A. Urquhart. Temporal Logic. Springer-Verlag, New York, 1971.

Stuart Russell and Eric Wefald. Principles of

metareasoning. Artificial Intelligence, 49(1-3):361--395, 1991.

R. Sun, T. Peterson, and C. Sessions. The extraction of planning knowledge from reinforcement learning neural networks. Proceedings of WIRN 2001, 2001.

Ron Sun. Integrating Rules and Connectionism for Robust Commonsense Reasoning. John Wiley and Sons, Inc., New York, 1994.

Ron Sun. Supplementing neural reinforcement learning with symbolic methods. In S. Wermeter and R. Sun, editors, Hybrid Neural Systems, pages 333--47. Berin: Springer-Verlag, 2000.

Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press, 1995.

David R. Traum, Carl F. Andersen, Waiyian Chong, Darsana Josyula, Yoshi Okamoto, Khemdut Purang, Michael O'Donovan-Anderson, and Don Perlis. Representations of dialogue state for domain and task independent meta-dialogue. Electronic Transactions on Artificial Intelligence, 3:125--152, 1999.

C. J. C. H. Watkins. Learning from Delayed Rewards, PhD thesis, Cambridge University, Cambridge, England, 1989.

C. J. C. H. Watkins and P. Dayan. Q-learning. Machine Learning, 8:279--292, 1992.

S. Wermeter and R. Sun. Hybrid Neural Systems, Springer-Verlag, Heidelberg, 2000.

Metadata

Repository Staff Only: item control page