Year: 2023
Type: preprint
Abstract: This paper examines a novel type of multi-agent problem, in which an agent makes multiple identical copies of itself in order to achieve a single agent task better or more efficiently. This strategy improves performance if the environment is noisy and the task is sometimes unachievable by a single agent copy. We propose a learning algorithm for this multicopy problem which takes advantage of the structure of the value function to efficiently learn how to balance the advantages and costs of adding additional copies.
Source: arXiv (Cornell University)
Authors: Wolfe, Alicia P., Diamond, Oliver, Goeler-Slough, Brigitte, Feuerman, Remi, Kisielinska, Magdalena, Manfredi, Victoria
Institution: Wesleyan University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
OpenAlex ID: W4386942699