ABSTRACT
The research presented here describes a framework that provides the necessary infrastructure to learn procedural knowledge from observation traces annotated with goal transition information. One instance of a learning-by-observation system, called KnoMic (Knowledge Mimic), is developed within this framework and evaluated in a complex domain. This evaluation demonstrates that learning by observation can acquire procedural knowledge and can acquire that knowledge more efficiently than standard knowledge acquisition.
- 1.M.Bain and C.Sammut.A framework for ehavioral cloning.In S.Muggleton,K.Furakawa,and D.Michie, editors,Machine Intelligence 14 Oxford University Press,1995. Google ScholarDigital Library
- 2.M.Bauer and C.Rich.Learning how to do things: Papers from the 2000 aaai fall symposium.Technical Report Technical Report FS-00-02,AAAI,2000.Google Scholar
- 3.S.S.Benson.Learning Action Models for Reactive Autonomous Agents. PhD thesis,Computer Science Dept.,Stanford University,1996. Google ScholarDigital Library
- 4.A.Billard and M.J.Mataric.A biologically inspired robotic model for learning y imitation.In Proceedings of the Fourth International Conference on Autonomous Agents. pages 373 -380,Barcelona, Catalonia,Spain,2000.ACM Press. Google ScholarDigital Library
- 5.B.G.Buchanan and D.C.Wilkins,editors.Readings in Knowledge Acquisition and Learning. Morgan Kaufman,1993. Google ScholarDigital Library
- 6.R.Calder,J.Smith,A.Courtemanche,J.Mar,and A.Ceranowicz.Modsaf ehavior simulation and control.In Proceedings of the Third Conference on Computer-Generated Forces and Behavioral Representation. 1993.Google Scholar
- 7.R.Cham ers and D.Michie.Boxes:An experiment on adaptive control.In E.Dale and D.Michie,editors, Machine Intelligence 2 pages 125 -133.1968.Google Scholar
- 8.R.E.Fikes and N.J.Nilsson.Strips:a new approach to the application of theorem proving to problem solving.Artificial Intelligence. 2:189 -208,1971.Google Scholar
- 9.Y.Gil and E.Melz.Explicit representations of problem-solving strategies to support knowledge acquisition.In Proceedings of the Thirteenth National Conference on Artificial Intelligence. pages 469 -476, 1996. Google ScholarDigital Library
- 10.R.M.Jones,J.E.Laird,P.E.Nielsen,K.J.Coulter, P.Kenny,and F.V.Koss.Automated intelligent pilots for combat .ight simulation.AI Magazine. 20:27 -41,1999.Google Scholar
- 11.J.E.Laird and M.C.van Lent.Human-level ai 's killer application:Interactive computer games.In Proceedings of the Eighteenth National Conference on Artificial Intelligence. 2000. Google ScholarDigital Library
- 12.T.M.Mitchell.Machine Learning McGraw-Hill,1997. Google ScholarDigital Library
- 13.D.J.Pearson and J.E.Laird.Towards incremental knowledge correction for agents in complex environments.In Machine Intelligence. volume 15. Oxford University Press,1996. Google ScholarDigital Library
- 14.J.R.Quinlan and R.M.Cameron-Jones.Com ining instance-based and model-based learning.In Proceedings of the Tenth International Conference on Machine Learning. pages 236 -243,1993.Google Scholar
- 15.C.Sammut,S.Hurst,D.Kedzier,and D.Michie. Learning to .y.In Proceedings of the Ninth International Conference on Machine Learning. pages 385 -393,1992. Google ScholarDigital Library
- 16.S.Schaal.Is imitation learning the route to humanoid robots?Trends in Cognitive Sciences 3:233 -242,1999.Google Scholar
- 17.W.Shen and H.A.Simon.Rule creation and rule learning through environmental exploration.In Proceedings of the International Joint Conference on Artificial Intelligence.pages 675 -680,1989.Google Scholar
- 18.M.C.van Lent and J.E.Laird.Learning hierarchical performance knowledge y observation.In Proceedings of the 1999 International Conference on Machine Learning. pages 229 -238,1999. Google ScholarDigital Library
- 19.X.Wang.Learning Planning Operators by Observation and Practice PhD thesis,Computer Science Dept., Carnegie Mellon University,1996.Google Scholar
Index Terms
- Learning procedural knowledge through observation
Recommendations
Integrating machine learning with knowledge acquisition through direct interaction with domain experts
Knowledge elicitation from experts and empirical machine learning are two distinct approaches to knowledge acquisition with differing and mutually complementary capabilities. Learning apprentices have provided environments in which a knowledge engineer ...
A knowledge creation info-structure to acquire and crystallize the tacit knowledge of health-care experts
Tacit knowledge of health-care experts is an important source of experiential know-how, yet due to various operational and technical reasons, such health-care knowledge is not entirely harnessed and put into professional practice. Emerging knowledge-...
MTLS: A Tool for Extending and Refining Knowledge Bases
ICTAI '97: Proceedings of the 9th International Conference on Tools with Artificial IntelligenceThis paper presents an interactive multistrategy learning system (MTLS) that extends and refines knowledge bases by learning from input examples, discovering new knowledge, and cooperating with a user. The use of the multistrategy learning approach ...
Comments