Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

Sparse kernel-SARSA(lambda) with an eligibility trace

Date

Authors

Robards, Matthew

Sunehag, Peter

Sanner, Scott

Marthi, Bhaskara

Publisher

Springer

Abstract

We introduce the first online kernelized version of SARSA(λ) to permit sparsification for arbitrary λ for 0 ≤ λ ≤ 1; this is possible via a novel kernelization of the eligibility trace that is maintained separately from the kernelized value functio

Keywords

Keywords: Basis functions; Capacity control; Eligibility traces; Functional structure; Kernelization; Memory efficiency; Projection techniques; Sparse kernels; Sparsification; Value functions; Learning systems

URI

http://hdl.handle.net/1885/83410

Collections

ANU Research Publications

Source

Proceedings of Machine Learning and Knowledge Discovery in Databases - European Conference (ECML PKDD 2011)

Type

Conference paper

DOI

10.1007/978-3-642-23808-6_1

Restricted until

2037-12-31

Downloads

File

Description

01_Robards_Sparse_kernel-SARSA(lambda)_2011.pdf (454.8 KB)