Repository logo
Research Data
Publications
Projects
Persons
Organizations
English
Français
Log In(current)
  1. Home
  2. Publications
  3. Acte de congrès (conference proceedings)
  4. Minimax-Bayes Reinforcement Learning

Minimax-Bayes Reinforcement Learning

Author(s)
Thomas Kleine Buening
Dimitrakakis, Christos  
Chaire de science des données  
Hannes Eriksson
Divya Grover
Emilio Jorge
Date issued
2023
In
PMLR
Vol
206
Abstract
While the Bayesian decision-theoretic framework offers an elegant solution to the problem of decision making under uncertainty, one question is how to appropriately select the prior distribution. One idea is to employ a worst-case prior. However, this is not as easy to specify in sequential decision making as in simple statistical estimation problems. This paper studies (sometimes approximate) minimax-Bayes solutions for various reinforcement learning problems to gain insights into the properties of the corresponding priors and policies. We find that while the worst-case prior depends on the setting, the corresponding minimax policies are more robust than those that assume a standard (i.e. uniform) prior.
Event name
AISTATS
Location
Valencia, Spain
Publication type
conference proceedings
Identifiers
https://libra.unine.ch/handle/20.500.14713/29876
-
https://libra.unine.ch/handle/123456789/32904
File(s)
Loading...
Thumbnail Image
Download
Name

buening23a.pdf

Type

Main Article

Size

1.11 MB

Format

Adobe PDF

Checksum

(MD5):4ac208e75cc59505b82b533a53462c36

Université de Neuchâtel logo

Service information scientifique & bibliothèques

Rue Emile-Argand 11

2000 Neuchâtel

contact.libra@unine.ch

Service informatique et télématique

Rue Emile-Argand 11

Bâtiment B, rez-de-chaussée

Powered by DSpace-CRIS

v2.0.0

© 2025 Université de Neuchâtel

Portal overviewUser guideOpen Access strategyOpen Access directive Research at UniNE Open Access ORCIDWhat's new