Abstract
A robotic agent experiences a world of continuous multivariate sensations and chooses its actions from continuous action spaces. Unless the agent is able to successfully partition these into functionally similar classes, its ability to interact with the world will be extremely limited. We present a method whereby an unsupervised robotic agent learns to discriminate discrete actions out of its continuous action parameters. These actions are discriminated because they lead to qualitatively distinct outcomes in the robot's sensor space. Once found, these actions can be used by the robot as primitives for further exploration of its world. We present results gathered using a Pioneer 1 mobile robot.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
R. Agrawal, K. Lin, H. S. Sawhney, and K. Shim. Fast similarity search in the presence of noise, scaling and translation in time series databases. In Proceedings of the 21st International Conference on Very Large Databases, 1995.
Scott Benson. Inductive learning of reactive action models. In Proceedings of the Twelfth International Conference on Machine Learning, pages 47–54, 1995.
Paul R. Cohen, Marco Ramoni, Paola Sebastiani, and John Warwick. Unsupervised clustering of robot activities: A bayesian approach. To appear in Proceedings of the Fourth International Conference on Autonomous Agents, 1999.
Thomas H. Cormen, Charles E. Leiserson, and Ronald L. Rivest. Introduction to Algorithms. The MIT Press, 1990.
Yolanda Gil. Acquiring Domain Knowledge for Planning by Experimentation. PhD thesis, Carnegie Mellon University, 1992.
Eamonn Keogh and Michael J. Pazzani. An enhanced representation of time series which allows fast and accurate classification, clustering and relevance feedback. In Working Notes of the AAAI-98 workshop on Predicting the Future: AI Approaches to Time-Series Analysis, pages 44–51, 1998.
Sridhar Mahadevan and Jonathan Connell. Automatic programming of behavior-based robots using reinforcement learning. Artificial Intelligence, 55(2-3):189–208, 1992.
Tim Oates. Identifying distinctive subsequences in multivariate time series by clustering. In Proceedings of the Fifth International Conference on Knowledge Discovery and Data Mining, pages 322–326, 1999.
Tim Oates and Paul R. Cohen. Searching for planning operators with context-dependent and probabilistic effects. 1996.
Tim Oates, Zachary Eyler-Walker, and Paul R. Cohen. Toward natural language interfaces for robotic agents: Grounding linguistic meaning in sensors. In Proceedings of the Fourth International Conference on Autonomous Agents, pages 227–228, 2000. Extended abstract.
David M. Pierce. Map Learning with Uninterpreted Sensors and Effector. PhD thesis, University of Texas, Austin, 1995.
David Sanko and Joseph B. Kruskal, editors. Time Warps, String Edits, and Macromolecules: Theory and Practice of Sequence Comparisons. Addison-Wesley Publishing Company, Reading, MA, 1983.
J. C. Santamaria, R. S. Sutton, and A. Ram. Experiments with reinforcement learning in problems with continuous state and action spaces. Adaptive behavior, 6(2):163–218, 1998.
Patrick Suppes. A Probabilistic Theory of Causality. North Holland, Amsterdam, 1970.
Xuemei Wang. Learning by observation and practice: An incremental approach for planning operator acquisition. In Proceedings of the Twelfth International Conference on Machine Learning, 1995.
Andreas S. Weigend, Morgan Mangeas, and Ashok N. Srivastava. Nonlinear gated experts for time series: discovering regimes and avoiding overfitting. Int J Neural Syst, 6:373–399, 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
King, G., Oates, T. (2001). The Importance of Being Discrete: Learning Classes of Actions and Outcomes through Interaction. In: Stroulia, E., Matwin, S. (eds) Advances in Artificial Intelligence. Canadian AI 2001. Lecture Notes in Computer Science(), vol 2056. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45153-6_23
Download citation
DOI: https://doi.org/10.1007/3-540-45153-6_23
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42144-3
Online ISBN: 978-3-540-45153-2
eBook Packages: Springer Book Archive