Integrating planning and learning: the PRODIGY architecture

DOI10.1080/09528139508953801MaRDI QIDQ4834396zbMATH OpenOpenAlexFDO

Authors Manuela M. Veloso, Jaime G. Carbonell, Alicia Pérez, Daniel Borrajo, Eugene Fink, Jim Blythe

Publication date 4 July 2000

Published in Journal of Experimental & Theoretical Artificial Intelligence (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/10016/6770

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Cites work

• Acquiring search-control knowledge via static analysis
• Automatically generating abstractions for planning
• Planning for conjunctive goals
• STRIPS: A new approach to the application of theorem proving to problem solving
• Theory and algorithms for plan merging

Cited in

(13)

• Automatically selecting and using primary effects in planning: Theory and experiments.
• Using genetic programming to learn and improve control knowledge.
• Using temporal logics to express search control knowledge for planning
• Knowledge-based proof planning
• Computing programs for generalized planning using a classical planner
• Proof planning with multiple strategies
• Efficient interactive decision-making framework for robotic applications
• Model-lite planning: case-based vs. model-based approaches
• Multi-agent plan based information gathering
• Action failure recovery via model-based diagnosis and conformant planning
• Planning under uncertainty as G<scp>OLOG</scp>programs
• Generalized planning as heuristic search: a new planning search-space that leverages pointers over objects
• Learning from planner performance

Describes a project that uses

Uses Software

• Prodigy

This page was built for publication: Integrating planning and learning: the PRODIGY architecture

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4834396)