Linear least-squares algorithms for temporal difference learning
Machine Learning - Special issue on reinforcement learning
Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Slow feature analysis: unsupervised learning of invariances
Neural Computation
Proto-value functions: developmental reinforcement learning
ICML '05 Proceedings of the 22nd international conference on Machine learning
Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems
Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems
Restricted gradient-descent algorithm for value-function approximation in reinforcement learning
Artificial Intelligence
On the relation of slow feature analysis and laplacian eigenmaps
Neural Computation
Incremental slow feature analysis
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Construction of approximation spaces for reinforcement learning
The Journal of Machine Learning Research
| Hi-index | 0.00 |
We show that Incremental Slow Feature Analysis (IncSFA) provides a low complexity method for learning Proto-Value Functions (PVFs). It has been shown that a small number of PVFs provide a good basis set for linear approximation of value functions in reinforcement environments. Our method learns PVFs from a high-dimensional sensory input stream, as the agent explores its world, without building a transition model, adjacency matrix, or covariance matrix. A temporal-difference based reinforcement learner improves a value function approximation upon the features, and the agent uses the value function to achieve rewards successfully. The algorithm is local in space and time, furthering the biological plausibility and applicability of PVFs.