Reference : An analytic solution to discrete Bayesian reinforcement learning
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/11055
An analytic solution to discrete Bayesian reinforcement learning
English
Poupart, Pascal [> >]
Vlassis, Nikos mailto [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
Hoey, Jesse [> >]
Regan, Kevin [> >]
2006
Proc Int. Conf. on Machine Learning, Pittsburgh, USA
697-704
Yes
Int. Conf. on Machine Learning, Pittsburgh, USA
2006
[en] Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms come short of achieving this goal because the amount of exploration required is often too costly and/or too time consuming for online learning. As a result, RL is mostly used for offline learning in simulated environments. We propose a new algorithm, called BEETLE, for effective online learning that is computationally efficient while minimizing the amount of exploration. We take a Bayesian model-based approach, framing RL as a partially observable Markov decision process. Our two main contributions are the analytical derivation that the optimal value function is the upper envelope of a set of multivariate polynomials, and an efficient point-based value iteration algorithm that exploits this simple parameterization.
http://hdl.handle.net/10993/11055

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
download.pdfPublisher postprint408.9 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.