New algorithms of the Q-learning type
- 1 April 2008
- journal article
- research article
- Published by Elsevier in Automatica
- Vol. 44 (4) , 1111-1119
Abstract
No abstract availableKeywords
This publication has 8 references indexed in Scilit:
- Two-timescale simultaneous perturbation stochastic approximation using deterministic perturbation sequencesACM Transactions on Modeling and Computer Simulation, 2003
- Call admission control and routing in integrated services networks using neuro-dynamic programmingIEEE Journal on Selected Areas in Communications, 2000
- Actor-Critic--Type Learning Algorithms for Markov Decision ProcessesSIAM Journal on Control and Optimization, 1999
- Stochastic approximation with two time scalesSystems & Control Letters, 1997
- A one-measurement form of simultaneous perturbation stochastic approximationAutomatica, 1997
- Asynchronous stochastic approximation and Q-learningMachine Learning, 1994
- Q-learningMachine Learning, 1992
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximationIEEE Transactions on Automatic Control, 1992