Benchmarking for Bayesian Reinforcement Learning

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been proposed, but the benchmarks used to compare them are only r...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	PloS one 2016-06, Vol.11 (6), p.e0157088-e0157088
Hauptverfasser:	Castronovo, Michael, Ernst, Damien, Couëtoux, Adrien, Fonteneau, Raphael
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Animals Artificial intelligence Bayes Theorem Bayesian analysis Bayesian reinforcement learning BBRL library Benchmarking - methods Benchmarks Biology and Life Sciences Choice Behavior Computational Biology - methods Computer and Information Sciences Computer science Computer Simulation Decision Making Distance learning Engineering and Technology Engineering, computing & technology Experiments Humans Ingénierie, informatique & technologie International conferences Knowledge Learning - physiology Libraries Machine learning Markov analysis Markov Chains Markov processes Methodology Offline learning Physical Sciences Probability distribution Problems Reinforcement Reinforcement (Psychology) Reproducibility of Results Research and Analysis Methods Reward Sciences informatiques Social Sciences
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!