A reinforcement learning system by using a mixture model of Bayesian network

A reinforcement learning system by using a mixture model of Bayesian network

In this research, we propose a system improving reinforcement learning agents' policies by using a mixture of Bayesian Networks (BNs) to adapt the agents to dynamic environments. A BN is one of stochastic models and used as agents' stochastic knowledge. In our system, models corresponding...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kitakoshi, D., Shioya, H., Kurihara, M.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Bayesian methods
Computer simulation
Stochastic processes
Stochastic systems
Supervised learning
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this research, we propose a system improving reinforcement learning agents' policies by using a mixture of Bayesian Networks (BNs) to adapt the agents to dynamic environments. A BN is one of stochastic models and used as agents' stochastic knowledge. In our system, models corresponding to new environments are represented by the mixture distribution of BNs constructed in advance.