Reinforcement Learning with Markov Logic Networks

Authors:
Weiwei Wang;Yang Gao;Xingguo Chen;Shen Ge
Affiliations:
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, PRC 210093;State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, PRC 210093;State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, PRC 210093;State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, PRC 210093
Venue:
MICAI '08 Proceedings of the 7th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
Year:
2008

Citing 8
Cited 0

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
Relational reinforcement learning

Machine Learning - Special issue on inducive logic programming
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Markov logic networks

Machine Learning
Entity Resolution with Markov Logic

ICDM '06 Proceedings of the Sixth International Conference on Data Mining
Autonomous transfer for reinforcement learning

Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
Unifying logical and statistical AI

AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Recursive random fields

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a method to combine reinforcement learning (RL) and Markov logic networks (MLN). RL usually does not consider the inherent relations or logical connections of the features. Markov logic networks combines first-order logic and graphical model and it can represent a wide variety of knowledge compactly and abstractly. We propose a new method, reinforcement learning algorithm with Markov logic networks (RLMLN), to deal with many difficult problems in RL which have much prior knowledge to employ and need some relational representation of states. With RLMLN, prior knowledge can be easily introduced to the learning systems and the learning process will become more efficient. Experiments on blocks world illustrate that RLMLN is a promising method.