Representation Discovery for Kernel-Based Reinforcement Learning
Recent years have seen increased interest in non-parametric reinforcement learning. There are now practical kernel-based algorithms for approximating value functions; however, kernel regression requires that the underlying function being approximated be smooth on its domain. Few problems of interest...
Main Authors: | Zewdie, Dawit H., Konidaris, George |
---|---|
Other Authors: | Leslie Kaelbling |
Published: |
2015
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/100053 |
Similar Items
-
Representation discovery in non-parametric reinforcement learning
by: Zewdie, Dawit (Dawit Habtamu)
Published: (2014) -
Kernel Geometric Mean Metric Learning
by: Zixin Feng, et al.
Published: (2023-11-01) -
Environment-Aware Adaptive Reinforcement Learning-Based Routing for Vehicular Ad Hoc Networks
by: Yi Jiang, et al.
Published: (2023-12-01) -
Parameter-free basis allocation for efficient multiple metric learning
by: Dongyeon Kim, et al.
Published: (2023-01-01) -
Learning Multimodal Representations by Symmetrically Transferring Local Structures
by: Bin Dong, et al.
Published: (2020-09-01)