Work

A note on the article "On Exploiting Spectral Properties for Solving MDP with Large State Space"

Year: 2021

Type: preprint

Abstract: We improve a theoretical result of the article "On Exploiting Spectral Properties for Solving MDP with Large State Space" showing that their algorithm, which was proved to converge under some unrealistic assumptions, is actually guaranteed to converge always.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2107.08488

Author: Maran, D.

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W3186938513

Cites: 1

Cited by:

Related to: 10