Efficient learning and planning within the Dyna framework
- 30 December 2002
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE International Conference on Neural Networks
- p. 168-174 vol.1
- https://doi.org/10.1109/icnn.1993.298551
Abstract
The Dyna class of reinforcement learning architectures enables the creation of integrated learning, planning and reacting systems. A class of strategies designed to enhance the learning and planning power of Dyna systems by increasing their computational efficiency is examined. The benefit of using these strategies is demonstrated on some simple abstract learning tasks. It is proposed that the backups to be performed in Dyna be prioritized in order to improve its efficiency. It is demonstrated with simple tasks that use some specific prioritizing schemes can lead to significant reductions in computational effort and corresponding improvements in learning performance.Keywords
This publication has 5 references indexed in Scilit:
- Q-learningMachine Learning, 1992
- Reinforcement learning is direct adaptive optimal controlIEEE Control Systems, 1992
- Planning by Incremental Dynamic ProgrammingPublished by Elsevier BV ,1991
- Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic ProgrammingPublished by Elsevier BV ,1990
- Learning to predict by the methods of temporal differencesMachine Learning, 1988