Supplementary material for Uncorrected least-squares temporal difference with lambda-return

TL;DR

This supplementary material supports the main paper on uncorrected least-squares temporal difference learning with lambda-return, providing additional details and data.

Contribution

It offers supplementary insights and data to enhance understanding of the uncorrected least-squares TD with lambda-return method.

Findings

Additional experimental results included

Extended theoretical analysis provided

Supporting data and proofs supplied

Abstract

Here, we provide a supplementary material for Takayuki Osogami, "Uncorrected least-squares temporal difference with lambda-return," which appears in {\it Proceedings of the 34th AAAI Conference on Artificial Intelligence} (AAAI-20).