ICAPS 04 Logo 14Th International Conference on Automated Planning & Scheduling

Whistler, British Columbia, Canada, June 3-7 2004
Welcome to ICAPS 2004
Registration Quicklink
Accommodation Quicklink
Author Instructions Quicklink
Program Quicklink
Doctoral Consortium

Tutorial 1. Planning and Learning


Current planning algorithms can achieve impressive performance in many domains and problems. However, there is still place for improvement among several dimensions, such as consideration of quality, dynamic changes in domain and quality descriptions, or integration of planning and scheduling (time and resources reasoning). One way to improve current fast algorithms consists on integrating machine learning with planning to automatically improve the planning domain description, performance or plan quality with experience. This tutorial will cover issues concerning representation of learned knowledge, learning opportunities of current planning techniques, and different learning approaches, including deterministic and nondeterministic planning.

Intended Audience

This tutorial is targeted at planning and scheduling researchers interested in providing learning capabilities to their planning & scheduling systems. It is also targeted at KR researchers given that we will address some knowledge representation issues related to structures for representing knowledge, or effects of representation changes with respect to learning and planning.

Presenters Information

Daniel Borrajo Daniel Borrajo is a Professor of Computer Science at Universidad Carlos III de Madrid. He has published over 90 journal and conference papers mainly in the field of machine learning and problem solving. Prof. Borrajo's main research interest is the integration of different Artificial Intelligence techniques, specially concerning machine learning and problem solving. Since 1989, he has been working with Prof. Carbonell and Prof. Veloso group in the Prodigy architecture, a planning system integrated with several learning modules. He developed Hamlet, a system that learns individual control knowledge for planning domains based on an incremental refinement of the learned knowledge. He is now interested on issues such as the integration of planning and scheduling, learning for improving the quality of the solutions, or new generalization techniques for reinforcement learning. Prof. Borrajo has organized several international conferences including ECP-01. He is currently member of the Network Executive Committee of PLANET, the European Research Network on Planning.
Manuela M. Veloso Manuela M. Veloso is Professor of Computer Science at Carnegie Mellon University. Prof. Veloso researches in the area of artificial intelligence with focus on planning, control learning, and execution for single and multirobot teams. Her algorithms address uncertain, dynamic, and adversarial environments. Prof. Veloso has developed teams of robot soccer agents, which have been RoboCup world champions several times. She investigates learning approaches to a variety of control problems, in particular the performance optimization of algorithm implementations, and plan recognition in complex data sets. Prof. Veloso is Vice President of the RoboCup International Federation. She was awarded an NSF Career Award in 1995 and the Allen Newell Medal for Excellence in Research in 1997. As of July 2003, she is a Fellow of the AAAI (American Association for Artificial Intelligence).

Tutorial URL: http://scalab.uc3m.es/~dborrajo/icaps04-tutorial/

Tutorial 1 Tutorial 2 Tutorial 3 Tutorial 4 Tutorial 5

Last modified: Tue Jun 15 08:59:14 Eastern Daylight Time 2004