Making a reinforcement learning agent believe

Authors:
Klaus Häming;Gabriele Peters
Affiliations:
University of Hagen - Human-Computer-Interaction, Hagen, Germany;University of Hagen - Human-Computer-Interaction, Hagen, Germany
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Year:
2012

Citing 2
Cited 0

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Handbook of automated reasoning

Handbook of automated reasoning

Quantified Score

Hi-index	0.00

Visualization

Abstract

We recently explored the benefits of a reinforcement learning agent which is supplemented by a symbolic learning level. This second level is represented in the symbolic form of Spohn's ranking functions. Given this context, we discuss in this paper the creation of symbolic rules from a Q-function. We explore several alternatives and show that the rule generation greatly influences the performance of the agent. We provide empirical evidence about which approach to favor. Additionally, the rules created by the considered application are shown to be plausible and understandable.