April 24, 2024, 4:41 a.m. | Alessandro Trenta, Davide Bacciu, Andrea Cossu, Pietro Ferrero

cs.LG updates on arXiv.org arxiv.org

arXiv:2404.14909v1 Announce Type: new
Abstract: We develop MultiSTOP, a Reinforcement Learning framework for solving functional equations in physics. This new methodology produces actual numerical solutions instead of bounds on them. We extend the original BootSTOP algorithm by adding multiple constraints derived from domain-specific knowledge, even in integral form, to improve the accuracy of the solution. We investigate a particular equation in a one-dimensional Conformal Field Theory.

abstract accuracy algorithm arxiv constraints cs.lg domain form framework functional hep-th integral knowledge methodology multiple numerical physics reinforcement reinforcement learning solutions them type

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US