Parametric value function approximation: A unified view - CentraleSupélec Access content directly
Conference Papers Year : 2011

Parametric value function approximation: A unified view

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. An important RL subtopic is to approximate this function when the system is too large for an exact representation. This survey reviews and unifies state of the art methods for parametric value function approximation by grouping them into three main categories: bootstrapping, residuals and projected fixed-point approaches. Related algorithms are derived by considering one of the associated cost functions and a specific way to minimize it, almost always a stochastic gradient descent or a recursive least-squares approach.
Fichier principal
Vignette du fichier
ADPRL_2011_MGOP.pdf (247.73 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00618112 , version 1 (31-08-2011)

Identifiers

Cite

Matthieu Geist, Olivier Pietquin. Parametric value function approximation: A unified view. ADPRL 2011, Apr 2011, Paris, France. pp.9-16, ⟨10.1109/ADPRL.2011.5967355⟩. ⟨hal-00618112⟩
85 View
567 Download

Altmetric

Share

Gmail Facebook X LinkedIn More