Robards, MatthewSunehag, PeterSanner, ScottMarthi, Bhaskara2015-12-13September9783642237799http://hdl.handle.net/1885/83410We 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 functioKeywords: Basis functions; Capacity control; Eligibility traces; Functional structure; Kernelization; Memory efficiency; Projection techniques; Sparse kernels; Sparsification; Value functions; Learning systems201110.1007/978-3-642-23808-6_12016-02-24