Towards a Self-Learning Agent: Using Ranking Functions as a Belief Representation in Reinforcement Learning

Authors:
Klaus Häming;Gabriele Peters
Affiliations:
University of Hagen, Hagen, Germany 58097;University of Hagen, Hagen, Germany 58097
Venue:
Neural Processing Letters
Year:
2013

Citing 10
Cited 0

On the logic of iterated belief revision

Artificial Intelligence
Relational reinforcement learning

Machine Learning - Special issue on inducive logic programming
The Architecture of Cognition

The Architecture of Cognition
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Handbook of automated reasoning

Handbook of automated reasoning
2007 Special Issue: The interaction of implicit learning, explicit hypothesis testing learning and implicit-to-explicit knowledge extraction

Neural Networks
Top-down induction of first-order logical decision trees

Artificial Intelligence
Conditionals in nonmonotonic reasoning and belief revision: considering conditionals as agents

Conditionals in nonmonotonic reasoning and belief revision: considering conditionals as agents
An alternative approach to the revision of ordinal conditional functions in the context of multi-valued logic

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
A fuzzy controller with supervised learning assisted reinforcement learning algorithm for obstacle avoidance

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a combination of belief revision and reinforcement learning which leads to a self-learning agent. The agent shows six qualities we deem necessary for a successful and adaptive learner. This is achieved by representing the agent's belief in two different levels, one numerical and one symbolical. While the former is implemented using basic reinforcement learning techniques, the latter is represented by Spohn's ranking functions. To make these ranking functions fit into a reinforcement learning framework, we studied the revision process and identified key weaknesses of the to-date approach. Despite the fact that the revision was modeled to support frequent updates, we propose and justify an alternative revision which leads to more plausible results. We show in an example application the benefits of the new approach, including faster learning and the extraction of learned rules.