Title :
Algorithmic Survey of Parametric Value Function Approximation
Author :
Geist, Matthieu ; Pietquin, Olivier
Author_Institution :
IMS-MaLIS Res. Group, Supelec, Metz, France
Abstract :
Reinforcement learning (RL) is a machine learning answer to the optimal control problem. It consists of learning an optimal control policy through interactions with the system to be controlled, the quality of this policy being quantified by the so-called value function. A recurrent subtopic of RL concerns computing an approximation of this value function when the system is too large for an exact representation. This survey reviews state-of-the-art methods for (parametric) value function approximation by grouping them into three main categories: bootstrapping, residual, and projected fixed-point approaches. Related algorithms are derived by considering one of the associated cost functions and a specific minimization method, generally a stochastic gradient descent or a recursive least-squares approach.
Keywords :
function approximation; gradient methods; learning (artificial intelligence); least squares approximations; optimal control; stochastic processes; RL recurrent subtopic; bootstrapping approach; cost function minimization method; machine learning; optimal control policy learning; parametric value function approximation; projected fixed-point approach; recursive least-squares approach; reinforcement learning; residual approach; stochastic gradient descent; Approximation algorithms; Cost function; Equations; Function approximation; Mathematical model; Supervised learning; Reinforcement learning (RL); survey; value function approximation;
Journal_Title :
Neural Networks and Learning Systems, IEEE Transactions on
DOI :
10.1109/TNNLS.2013.2247418
