Search
 
loader loading subjects...
cover
Q-Learning as Failure
Kei Takahata, Takao Miura
343 - 354
10.3233/FAIA200839
Research Article
Frontiers in Artificial Intelligence and Applications
Volume 333: Information Modelling and Knowledge Bases XXXII
Abstract

Reinforcement Learning allows us to acquire knowledge without any training data. However, for learning it takes time. In this work, we propose a method to perform Reverse action by using Retrospective Kalman Filter that estimates the state one step before. We show an experience by a Hunter Prey problem. And discuss the usefulness of our proposed method.

Download
Creative Commons License