To Discount or not to Discount in Reinforcement Learning: A Case Study Comparing R Learning and Q Learning
Author:
- Sridhar MahadevanSMSridhar Mahadevan
- 1 January 1994
- book chapter
- Published by Elsevier
- p. 164-172
Abstract
No abstract availableKeywords
This publication has 5 references indexed in Scilit:
- A Reinforcement Learning Method for Maximizing Undiscounted Rewards1993
- Automatic programming of behavior-based robots using reinforcement learningArtificial Intelligence, 1992
- Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming1990
- Learning to predict by the methods of temporal differencesMachine Learning, 1988
- Neuronlike adaptive elements that can solve difficult learning control problemsIEEE Transactions on Systems, Man, and Cybernetics, 1983