Reference : Bayesian Reinforcement Learning
Parts of books : Contribution to collective works
Engineering, computing & technology : Computer science
Bayesian Reinforcement Learning
Vlassis, Nikos mailto [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
Ghavamzadeh, Mohammad [> >]
Mannor, Shie [> >]
Poupart, Pascal [> >]
Reinforcement Learning: State of the Art
Wiering, Marco
van Otterlo, Martijn
[en] This chapter surveys recent lines of work that use Bayesian techniques for reinforcement learning. In Bayesian learning, uncertainty is expressed by a prior distribution over unknown parameters and learning is achieved by computing a posterior distribution based on the data observed. Hence, Bayesian reinforcement learning distinguishes itself from other forms of reinforcement learning by explic- itly maintaining a distribution over various quantities such as the parameters of the model, the value function, the policy or its gradient. This yields several benefits: a) domain knowledge can be naturally encoded in the prior distribution to speed up learning; b) the exploration/exploitation tradeoff can be naturally optimized; and c) notions of risk can be naturally taken into account to obtain robust policies.
Luxembourg Centre for Systems Biomedicine (LCSB): Machine Learning (Vlassis Group)

File(s) associated to this reference

Fulltext file(s):

Open access
BRLchapter.pdfAuthor postprint196.55 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.