Multi-agent reinforcement learning for convex optimization

Autor:	Brian Maguire, Amir Morcos, Aaron West
Rok vydání:	2021
Předmět:	Action (philosophy) Computer science business.industry Frame (networking) Convex optimization Rapid convergence Reinforcement learning State (computer science) Artificial intelligence Space (commercial competition) business
Zdroj:	Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III.
DOI:	10.1117/12.2585624
Popis:	Multi-Agent Reinforcement Learning (RL) algorithms have recently demonstrated their ability to discover/develop new strategies to solving problems. This work aims to apply this same methodology to solving convex optimization problems in an attempt to train agents to outperform popular optimizers. This work will examine methods to frame the problem to the RL agents which encourage rapid convergence. Additionally we will discuss the various ways to represent the environment or state that the agents will operate in, as well as the action space and rewards.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::752a41bc1f2058f283e26b209d1cf192 https://doi.org/10.1117/12.2585624 Zobrazit plný text záznamu