A Concentration Bound for LSPE($\lambda$)
Machine Learning
2022-12-01 v5 Systems and Control
Systems and Control
Abstract
The popular LSPE() algorithm for policy evaluation is revisited to derive a concentration bound that gives high probability performance guarantees from some time on.
Cite
@article{arxiv.2111.02644,
title = {A Concentration Bound for LSPE($\lambda$)},
author = {Siddharth Chandak and Vivek S. Borkar and Harsh Dolhare},
journal= {arXiv preprint arXiv:2111.02644},
year = {2022}
}
Comments
17 pages, accepted for publication in Systems and Control Letters