Title :
Asynchronous stochastic approximation and Q-learning
Author :
Tsitsiklis, John N.
Author_Institution :
Lab. for Inf. & Decision Syst., MIT, Cambridge, MA, USA
Abstract :
Provides some general results on the convergence of a class of stochastic approximation algorithms and their parallel and asynchronous variants. The author then uses these results to study the Q-learning algorithm, a reinforcement learning method for solving Markov decision problems, and establishes its convergence under conditions more general than previously available
Keywords :
Markov processes; convergence; decision theory; dynamic programming; learning (artificial intelligence); Markov decision problems; Q-learning; asynchronous stochastic approximation; convergence; reinforcement learning method; Adaptive control; Approximation algorithms; Computational modeling; Convergence; Costs; Dynamic programming; Laboratories; Learning systems; Random variables; Stochastic processes;
Conference_Titel :
Decision and Control, 1993., Proceedings of the 32nd IEEE Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-1298-8
DOI :
10.1109/CDC.1993.325119
