Abstract
We are developing an integrated system for planning and learning. The type of learning we are interested in is advice-taking, or learning by being told. Our model of planning is based on the Reactive Action Packages (RAPs) of Firby (1989). Our model of learning is based on the Direct Memory Access Parser (DMAP) of Martin (1990).
- Firby, J. 1989. Adaptive Execution in Complex Dynamic Worlds. Ph.D. dissertation, Yale University. Google ScholarDigital Library
- Firby, J. and Hanks, S. 1987. The simulator manual. Technical report YALEU/CSD/RR #563, Computer Science Department, Yale University.Google Scholar
- Martin, C. 1990. Direct Memory Access Parsing. Ph.D. dissertation, Yale University. Google ScholarDigital Library
Index Terms
- An integrated architecture for planning and learning
Recommendations
An Integrated Approach of Learning, Planning, and Execution
Agents (hardware or software) that act autonomously in an environment have to be able to integrate three basic behaviors: planning, execution, and learning. This integration is mandatory when the agent has no knowledge about how its actions can affect ...
Dyna, an integrated architecture for learning, planning, and reacting
Dyna is an AI architecture that integrates learning, planning, and reactive execution. Learning methods are used in Dyna both for compiling planning results and for updating a model of the effects of the agent's actions on the world. Planning is ...
An integrated architecture for learning and planning in robotic domains
Our system, GINKO, is fully implemented and integrates aspects of Learning, Planning, Execution, Perception, and Robotics In short, from Robotics we take our domains and we borrow the notion of planning in configuration space. We use Machine Learning ...
Comments