Inductive Learning of Reactive Action Models

An important area of learning in autonomous agents is the ability to learn domain-specific models of actions to be used by planning systems. In this paper, we present methods by which an agent learns action models from its own experience and from its observation of a domain expert. These methods differ from previous work in the area in two ways: the use of an action model formalism which is better suited to the needs of a reactive agent, and successful implementation of noise-handling mechanisms. Training instances are generated from experience and observation, and a variant of GOLEM is used to learn action models from these instances. The integrated learning system has been experimentally validated in simulated construction and office domains.

[1]  Maurice Bruynooghe,et al.  Using the event calculus to integrate planning and learning in an intelligent autonomous agent , 1994 .

[2]  Wei-Min Shen,et al.  Autonomous learning from the environment , 1994 .

[3]  Richard Fikes,et al.  STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving , 1971, IJCAI.

[4]  Joseph Bates,et al.  Virtual Reality, Art, and Entertainment , 1992, Presence: Teleoperators & Virtual Environments.

[5]  Saso Dzeroski,et al.  Inductive Logic Programming: Techniques and Applications , 1993 .

[6]  Derek Sleeman,et al.  Machine learning : proceedings of the ninth international workshop (ML92) , 1992 .

[7]  Ben J. A. Kröse,et al.  Learning from delayed rewards , 1995, Robotics Auton. Syst..

[8]  Allen Newell,et al.  GPS, a program that simulates human thought , 1995 .

[9]  Sridhar Mahadevan,et al.  Enhancing Transfer in Reinforcement Learning by Building Stochastic Models of Robot Actions , 1992, ML.

[10]  Alan D. Christiansen.  Manipulation planning for empirical backprojections , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[11]  John McCarthy,et al.  SOME PHILOSOPHICAL PROBLEMS FROM THE STANDPOINT OF ARTI CIAL INTELLIGENCE , 1987 .

[12]  Stephen Muggleton,et al.  Efficient Induction of Logic Programs , 1990, ALT.

[13]  Yolanda Gil,et al.  Acquiring domain knowledge for planning by experimentation , 1992 .

[14]  Dana H. Ballard,et al.  Active Perception and Reinforcement Learning , 1990, Neural Computation.

[15]  Steven A. Vere,et al.  Multilevel Counterfactuals for Generalizations of Relational Concepts and Productions , 1980, Artif. Intell..

[16]  E. Mazer,et al.  On manipulation planning , 1995, Proceedings. IEEE International Symposium on Assembly and Task Planning.

[17]  Russell H. Taylor,et al.  Automatic Synthesis of Fine-Motion Strategies for Robots , 1984 .

[18]  Saso Dzeroski,et al.  Learnability of Constrained Logic Programs , 1993, ECML.

[19]  Claude Sammut,et al.  Learning to Fly , 1992, ML.

[20]  Xuemei Wang,et al.  Learning Planning Operators by Observation and Practice , 1994, AIPS.

[21]  Nils J. Nilsson,et al.  Reacting, Planning, and Learning in an Autonomous Agent , 1996, Machine Intelligence 14.

[22]  Nils J. Nilsson,et al.  Teleo-Reactive Programs for Agent Control , 1993, J. Artif. Intell. Res..

[23]  Marcel Schoppers,et al.  Building plans to monitor and exploit open-loop and closed-loop dynamics , 1992 .