Asynchronous Stochastic Approximation and Q-Learning. Tsitsiklis, J. N 1994.
abstract   bibtex   
We provide some general results on the convergence of a class of stochastic approximationalgorithms and their parallel and asynchronous variants. We then use these results to study the Q-learning algorithm, a reinforcement learning method for solving Markov decision problems, and establish its convergence under conditions more general than previously available.
@article{tsitsiklis_asynchronous_1994,
	title = {Asynchronous {Stochastic} {Approximation} and {Q}-{Learning}},
	abstract = {We provide some general results on the convergence of a class of stochastic approximationalgorithms and their parallel and asynchronous variants. We then use these results to study the Q-learning algorithm, a reinforcement learning method for solving Markov decision problems, and establish its convergence under conditions more general than previously available.},
	language = {en},
	author = {Tsitsiklis, John N},
	year = {1994},
	pages = {18},
}

Downloads: 0