A Self-Help Guide for Autonomous Systems

A Self-Help Guide for Autonomous Systems (2008)

Cached

Download Links

by Michael L. Anderson , Scott Fults , Darsana P. Josyula , Tim Oates , Don Perlis , Matt Schmill , Shomir Wilson , Dean Wright

Citations:

6 - 5 self

BibTeX

@MISC{Anderson08aself-help,
    author = {Michael L. Anderson and Scott Fults and Darsana P. Josyula and Tim Oates and Don Perlis and Matt Schmill and Shomir Wilson and Dean Wright},
    title = { A Self-Help Guide for Autonomous Systems},
    year = {2008}
}

Bookmark

OpenURL

Abstract

Humans learn from their mistakes. When things go badly, we notice that something is amiss, figure out what went wrong and why, and attempt to repair the problem. Artificial systems depend on their human designers to program in responses to every eventuality and therefore typically don’t even notice when things go wrong, following their programming over the proverbial, and in some cases literal, cliff. This article describes our past and current work on the metacognitive loop, a domain-general approach to giving artificial systems the ability to notice, assess, and repair problems. The

Citations

179	A model-based approach to reactive self-configuring systems - Williams, Nayak - 1996
90	Reasoning situation in time I: Basic concepts - Elgot-Drapkin, Perlis - 1990
71	Becoming increasingly reactive - Mitchell - 1990
49	Learning by experimentation: Incremental refinement of incomplete planning domains - Gil - 1994
48	Introspective multistrategy learning: On the construction of learning strategies - Cox, Ram - 1999
46	Creativity and Learning in a Case-Based Explainer - Schank, Leake - 1990
42	Learning by observation and practice: An incremental approach for planning operator acquisition - Wang - 1995
41	Pandurang Nayak. A model-based approach to reactive selfconfiguring systems - Williams, P - 1996
31	D.: Using introspective reasoning to refine indexing - Fox, Leake - 1995
29	Robust understanding in a dialogue system - Allen, Miller, et al. - 1996
23	Conversational adequacy: mistakes are the essence - Perlis, Purang, et al. - 1998
17	Learning to Anticipate and Avoid Planning Problems through the Explanation of Failures - Hammond - 1986
13	Monitored execution of robot plans produced by STRIPS - Fikes - 1971
12	Logic, self-awareness and selfimprovement: The metacognitive loop a nd the problem of brittleness - Anderson, Perlis
12	Redesigning a Problem-Solver’s Operations to Improve Solution Quality - Stroulia, Goel - 1997
12	A review of recent research in metareasoning and metalearning - Anderson, Oates - 2007
11	A resource based framework for planning and replanning. Web Intelligence and Agent Systems 1(3/4):173–186 - Krogt, Weerdt, et al. - 2003
9	Vcrtical and horizontal processes in problem solving - Kendler, Kendler
8	Utilization of metacognitive judgments in the allocation of study during multitria l learning - Nelson, Dunlosky, et al. - 1994
6	A Unified Theory of Acting and Agency for a Universal Interfacing Agent - Josyula - 2005
5	Reversal-shift behavior: Some basic issues - Kendler, Kendler - 1969
4	The Metacognitive Loop: Enhancing Reinforcement Learning with Metacognitive Monitoring and Control for Improved Perturbation Tolerance - Anderson, Oates, et al. - 2006
2	Waiyian Chong, Darsana Josyula, Yoshi Okamoto, Khemdut Purang, Michael O’Donovan-Anderson, and Don Perlis. Representations of dialogue state for domain and task independent metadialogue - Traum, Andersen - 1999
1	More Than the Sum of its Parts - AI - 2006
1	der Krogt et al. A resource based framework for planning and replanning. Web Intelligence and Agent System - van - 2003
1	Self-Improvement: The Meta Cognitive Loop and the Problem of Brittleness - Anderson, Perlis
1	graduated in 2006 from the University of Maryland with a Ph.D. in linguistics. His dissertation was concerned with how humans talk about and understand comparisons. He is currently a research scientist at the University of Maryland and works with Don Perl - Fults
1	Josyula is an assistant professor of computer SUMMER 2008 75 New Proceedings! Available from AAAI Press (www.aaai.org/Press/) science at - Darsana
1	completed her Ph.D. in 2005 from the - She
1	is an associate professor in the Department of Computer Science and Electrical Engineering at the University of Maryland Baltimore County, and he is director of the university’s Cognition, Robotics, and Learning Laboratory. He received his Ph.D. from the - Oates
1	Schmill is a researcher at the University of Maryland, Baltimore County. He received his PhD from the University of Massachusetts in 2004. His research interests include development, metacognition, building robust AI architectures, and computational finan - Matthew