@COMMENT This file was generated by bib2html.pl version 0.90
@COMMENT written by Patrick Riley
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@article{IEEETAC2020-koppel,
author={Alec Koppel and Garrett Warnell and Ethan Stump and Peter Stone and Alejandro Ribeiro},
journal={IEEE Transactions on Automatic Control},
title={Policy Evaluation in Continuous MDPs with Efficient Kernelized Gradient Temporal Difference},
year={2020},
abstract={We consider policy evaluation in infinite-horizon discounted Markov decision
problems (MDPs) with continuous compact state and action spaces. We reformulate
this task as a compositional stochastic program with a function-valued decision
variable that belongs to a reproducing kernel Hilbert space (RKHS). We approach
this problem via a new functional generalization of stochastic quasi-gradient
methods operating in tandem with stochastic sparse subspace projections. The
result is an extension of gradient temporal difference learning that yields
nonlinearly parameterized value function estimates of the solution to the
Bellman evaluation equation. We call this method Parsimonious Kernel Gradient
Temporal Difference (PKGTD) Learning. Our main contribution is a
memory-efficient non-parametric stochastic method guaranteed to converge
exactly to the Bellman fixed point with probability $1$ with attenuating
step-sizes under the hypothesis that it belongs to the RKHS. Further, with
constant step-sizes and compression budget, we establish mean convergence to a
neighborhood and that the value function estimates have finite complexity. In
the Mountain Car domain, we observe faster convergence to lower Bellman error
solutions than existing approaches with a fraction of the required memory.}
}