The actor-critic algorithm as multi-time-scale stochastic approximation
Authors:
- 1 August 1997
- journal article
- Published by Springer Nature in Sādhanā
- Vol. 22 (4) , 525-543
Abstract
No abstract availableKeywords
This publication has 10 references indexed in Scilit:
- A reinforcement learning neural network for adaptive control of Markov chainsIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 1997
- A tutorial survey of reinforcement learningSādhanā, 1994
- Markov Decision Processes1994
- Nonconvergence to Unstable Points in Urn Models and Stochastic ApproximationsThe Annals of Probability, 1990
- Adaptive Algorithms and Stochastic Approximations1990
- Convergent activation dynamics in continuous time networksNeural Networks, 1989
- Estimation and control in discounted stochastic dynamic programmingStochastics, 1987
- Generalized polynomial approximations in Markovian decision processesJournal of Mathematical Analysis and Applications, 1985
- Stochastic Approximation Methods for Constrained and Unconstrained Systems1978
- Chaotic relaxationLinear Algebra and its Applications, 1969