An algorithmic Survey of Parametric Value Function Approximation

Matthieu Geist 1 Olivier Pietquin 2
2 IMS - Equipe Information, Multimodalité et Signal
UMI2958 - Georgia Tech - CNRS [Metz], SUPELEC-Campus Metz
Abstract : Reinforcement learning is a machine learning answer to the optimal control problem. It consists in 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 reinforcement learning is to compute 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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [93 references]  Display  Hide  Download

https://hal-supelec.archives-ouvertes.fr/hal-00869725
Contributor : Sébastien van Luchene <>
Submitted on : Monday, November 6, 2017 - 5:33:08 PM
Last modification on : Wednesday, July 31, 2019 - 4:18:03 PM

File

vfa_survey.pdf
Files produced by the author(s)

Identifiers

Citation

Matthieu Geist, Olivier Pietquin. An algorithmic Survey of Parametric Value Function Approximation. IEEE Transactions on Neural Networks and Learning Systems, IEEE, 2013, 24 (6), pp.845-867. ⟨10.1109/TNNLS.2013.2247418⟩. ⟨hal-00869725⟩

Share

Metrics

Record views

205

Files downloads

202