Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Classes of kernels for machine learning: a statistics perspective
The Journal of Machine Learning Research
A tutorial on support vector regression
Statistics and Computing
Reinforcement learning with Gaussian processes
ICML '05 Proceedings of the 22nd international conference on Machine learning
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Evolutionary Function Approximation for Reinforcement Learning
The Journal of Machine Learning Research
Least Squares SVM for Least Squares TD Learning
Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
Efficient reinforcement learning with relocatable action models
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Feature Selection for Value Function Approximation Using Bayesian Model Selection
ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part I
Hessian matrix distribution for Bayesian policy gradient reinforcement learning
Information Sciences: an International Journal
Learning form experience: a bayesian network based reinforcement learning approach
ICICA'11 Proceedings of the Second international conference on Information Computing and Applications
Online learning with multiple kernels: A review
Neural Computation
Linear Bayesian reinforcement learning
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Hi-index | 0.00 |
Kernel-based Bayesian methods for Reinforcement Learning (RL) such as Gaussian Process Temporal Difference (GPTD) are particularly promising because they rigorously treat uncertainty in the value function and make it easy to specify prior knowledge. However, the choice of prior distribution significantly affects the empirical performance of the learning agent, and little work has been done extending existing methods for prior model selection to the online setting. This paper develops Replacing-Kernel RL, an online model selection method for GPTD using sequential Monte-Carlo methods. Replacing-Kernel RL is compared to standard GPTD and tile-coding on several RL domains, and is shown to yield significantly better asymptotic performance for many different kernel families. Furthermore, the resulting kernels capture an intuitively useful notion of prior state covariance that may nevertheless be difficult to capture manually.