Bayesian Reward Filtering

Abstract : A wide variety of function approximation schemes have been applied to reinforcement learning. However, Bayesian filtering approaches,which have been shown efficient in other fields such as neural network training, have been little studied.We propose a general Bayesian filtering framework for reinforcement learning, as well as a specific implementation based on sigma point Kalman filtering and kernel machines. This allows us to derive an efficient off-policy model-free approximate temporal differences algorithm which will be demonstrated on two simple benchmarks.
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00351282
Contributor : Sébastien van Luchene <>
Submitted on : Thursday, January 8, 2009 - 7:25:09 PM
Last modification on : Wednesday, February 13, 2019 - 5:20:08 PM

Links full text

Identifiers

Collections

Citation

Matthieu Geist, Olivier Pietquin. Bayesian Reward Filtering. EWRL 2008, Jun 2008, Lille, France. pp.96-109, ⟨10.1007/978-3-540-89722-4_8⟩. ⟨hal-00351282⟩

Share

Metrics

Record views

62