Incremental Multi-Step Q-Learning
- 1 January 1994
- book chapter
- Published by Elsevier BV
Abstract
No abstract availableKeywords
This publication has 8 references indexed in Scilit:
- Prioritized sweeping: Reinforcement learning with less data and less timeMachine Learning, 1993
- On the Convergence of Stochastic Iterative Dynamic Programming AlgorithmsPublished by Defense Technical Information Center (DTIC) ,1993
- Efficient Learning and Planning Within the Dyna FrameworkAdaptive Behavior, 1993
- The convergence of TD(?) for general ?Machine Learning, 1992
- Q-learningMachine Learning, 1992
- Consistency of HDP applied to a simple reinforcement learning problemNeural Networks, 1990
- 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