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
{"_id":{"_str":"534279610e946d920a00144e"},"__v":1,"authorIDs":[],"author_short":["Tsitsiklis, J. N"],"bibbaseid":"tsitsiklis-asynchronousstochasticapproximationandqlearning-1994","bibdata":{"bibtype":"article","type":"article","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":[{"propositions":[],"lastnames":["Tsitsiklis"],"firstnames":["John","N"],"suffixes":[]}],"year":"1994","pages":"18","bibtex":"@article{tsitsiklis_asynchronous_1994,\n\ttitle = {Asynchronous {Stochastic} {Approximation} and {Q}-{Learning}},\n\tabstract = {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.},\n\tlanguage = {en},\n\tauthor = {Tsitsiklis, John N},\n\tyear = {1994},\n\tpages = {18},\n}\n\n","author_short":["Tsitsiklis, J. N"],"key":"tsitsiklis_asynchronous_1994","id":"tsitsiklis_asynchronous_1994","bibbaseid":"tsitsiklis-asynchronousstochasticapproximationandqlearning-1994","role":"author","urls":{},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mxmplx","downloads":0,"keywords":[],"search_terms":["asynchronous","stochastic","approximation","learning","tsitsiklis"],"title":"Asynchronous Stochastic Approximation and Q-Learning","year":1994,"dataSources":["2cjnbEWxd35GBeqEe","aXmRAq63YsH7a3ufx"]}