The nature of statistical learning theory
The nature of statistical learning theory
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Machine Learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Kernel-Based Reinforcement Learning
Machine Learning
Integrating Experimentation and Guidance in Relational Reinforcement Learning
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Relational Reinforcement Learning
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Ridge Regression Learning Algorithm in Dual Variables
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Practical Reinforcement Learning in Continuous Spaces
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Everything old is new again: a fresh look at historical approaches in machine learning
Everything old is new again: a fresh look at historical approaches in machine learning
A survey of kernels for structured data
ACM SIGKDD Explorations Newsletter
Cyclic pattern kernels for predictive graph mining
Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Integrating Guidance into Relational Reinforcement Learning
Machine Learning
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Practical solution techniques for first-order MDPs
Artificial Intelligence
Learning gas distribution models using sparse Gaussian process mixtures
Autonomous Robots
Relevance Grounding for Planning in Relational Domains
ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part I
First order decision diagrams for relational MDPs
Journal of Artificial Intelligence Research
Learning models of relational MDPs using graph kernels
MICAI'07 Proceedings of the artificial intelligence 6th Mexican international conference on Advances in artificial intelligence
An autonomic testing framework for IPv6 configuration protocols
AIMS'10 Proceedings of the Mechanisms for autonomous management of networks and services, and 4th international conference on Autonomous infrastructure, management and security
Exploration in relational worlds
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part II
Automatic induction of bellman-error features for probabilistic planning
Journal of Artificial Intelligence Research
Planning with noisy probabilistic relational rules
Journal of Artificial Intelligence Research
Exploration in relational domains for model-based reinforcement learning
The Journal of Machine Learning Research
Reinforcement learning algorithms with function approximation: Recent advances and applications
Information Sciences: an International Journal
| Hi-index | 0.00 |
RRL is a relational reinforcement learning system based on Q-learning in relational state-action spaces. It aims to enable agents to learn how to act in an environment that has no natural representation as a tuple of constants. For relational reinforcement learning, the learning algorithm used to approximate the mapping between state-action pairs and their so called Q(uality)-value has to be very reliable, and it has to be able to handle the relational representation of state-action pairs. In this paper we investigate the use of Gaussian processes to approximate the Q-values of state-action pairs. In order to employ Gaussian processes in a relational setting we propose graph kernels as a covariance function between state-action pairs. The standard prediction mechanism for Gaussian processes requires a matrix inversion which can become unstable when the kernel matrix has low rank. These instabilities can be avoided by employing QR-factorization. This leads to better and more stable performance of the algorithm and a more efficient incremental update mechanism. Experiments conducted in the blocks world and with the Tetris game show that Gaussian processes with graph kernels can compete with, and often improve on, regression trees and instance based regression as a generalization algorithm for RRL.