Max-plus approximation for reinforcement learning

DOI10.1016/j.automatica.2021.109623OpenAlexW3153693640MaRDI QIDQ2665124

Vinicius Mariano Gonçalves

Publication date: 18 November 2021

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2021.109623

zbMATH Keywords

dynamic programmingreinforcement learningmax-plus algebra

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Related Items (1)

Approximately global optimal control for max-plus linear systems and its application on load distribution

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Tropical linear-fractional programming and parametric mean payoff games
• On the control of max-plus linear system subject to state restriction
• \({\mathcal Q}\)-learning
• On max-plus linear dynamical system theory: the regulation problem
• TROPICAL POLYHEDRA ARE EQUIVALENT TO MEAN PAYOFF GAMES
• The Max-Plus Finite Element Method for Solving Deterministic Optimal Control Problems: Basic Properties and Convergence Analysis
• Multidimensional binary search trees used for associative searching
• Max-Plus $(A,B)$-Invariant Spaces and Control of Timed Discrete-Event Systems
• Model predictive control for max-plus-linear discrete event systems

This page was built for publication: Max-plus approximation for reinforcement learning