Nov 17, 2018 · Abstract:The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free ...
This paper considers a recent variant of the GP-SarSA algorithm, called Sparse Pseudo-input Gaussian Process SARSA (SPGP-SARSA), and derive recursive ...
The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free Reinforcement Learning.
The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free Reinforcement Learning.
We present a new Gaussian process (GP) regression model whose covariance is parameterized by the the locations of M pseudo-input points.
Missing: Recursive SARSA.
[PDF] Sparse Gaussian Process Temporal Difference Learning for Marine ...
proceedings.mlr.press › ...
3 Sparse Pseudo-input Gaussian Process Temporal Difference Learning. The GP-SARSA method requires an expensive N × N matrix inversion, costing O(N3). Since ...
Oct 2, 2018 · Abstract: We present a method for Temporal Difference (TD) learning that ad- dresses several challenges faced by robots learning to navigate ...
To address this issue, a recursive online sparse Gaussian Process (GP)-based learning strategy for attitude takeover control of noncooperative targets with ...
Missing: SARSA. | Show results with:SARSA.
The results show SPGP-SARSA can outperform the state-of-the-art sparse method, replicate the prediction quality of its exact counterpart, and be applied to ...
This web site aims to provide an overview of resources concerned with probabilistic modeling, inference and learning based on Gaussian processes.