Guardado en:
Detalles Bibliográficos
Autores principales: Peri, Gianluca, Buffoni, Lorenzo, Chiti, Giacomo, Fanelli, Duccio, Marino, Raffaele, Nocentini, Andrea, Panti, Pier Paolo
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.22235
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914468735221760
author Peri, Gianluca
Buffoni, Lorenzo
Chiti, Giacomo
Fanelli, Duccio
Marino, Raffaele
Nocentini, Andrea
Panti, Pier Paolo
author_facet Peri, Gianluca
Buffoni, Lorenzo
Chiti, Giacomo
Fanelli, Duccio
Marino, Raffaele
Nocentini, Andrea
Panti, Pier Paolo
contents We study the statistical properties of trainable agents moving in discrete space. After introducing the mathematical framework, we first analyze the dynamics of two completely random walkers, mutually competing in a chaser-target interaction scheme. The statistics of the encounters is analytically obtained and the predictions tested versus numerical simulations. We then move forward to extend the baseline case to agents capable of learning and adapting to an external reward signal, using reinforcement learning. Smart walkers morph the statistics of the encounter, to maximize their cumulated reward, as confirmed by combined numerical and analytical insights. More interestingly, configuration entropy proves a reliable proxy to gauge the acquired ability of the agents to cope with the assigned task when no other information about them (i.e. reward signal, policy, etc) is present. We further test the proposed measure of learned skills by operating the Stockfish chess engine against a quasi-random untrained opponent. The obtained conclusions corroborate our claim. Summing up, our primary contribution is to propose and test a quantitative measure of agents' awareness that naturally correlates with the inherent complexity of the task being performed.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22235
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Smart Walkers in Discrete Space
Peri, Gianluca
Buffoni, Lorenzo
Chiti, Giacomo
Fanelli, Duccio
Marino, Raffaele
Nocentini, Andrea
Panti, Pier Paolo
Statistical Mechanics
We study the statistical properties of trainable agents moving in discrete space. After introducing the mathematical framework, we first analyze the dynamics of two completely random walkers, mutually competing in a chaser-target interaction scheme. The statistics of the encounters is analytically obtained and the predictions tested versus numerical simulations. We then move forward to extend the baseline case to agents capable of learning and adapting to an external reward signal, using reinforcement learning. Smart walkers morph the statistics of the encounter, to maximize their cumulated reward, as confirmed by combined numerical and analytical insights. More interestingly, configuration entropy proves a reliable proxy to gauge the acquired ability of the agents to cope with the assigned task when no other information about them (i.e. reward signal, policy, etc) is present. We further test the proposed measure of learned skills by operating the Stockfish chess engine against a quasi-random untrained opponent. The obtained conclusions corroborate our claim. Summing up, our primary contribution is to propose and test a quantitative measure of agents' awareness that naturally correlates with the inherent complexity of the task being performed.
title Smart Walkers in Discrete Space
topic Statistical Mechanics
url https://arxiv.org/abs/2601.22235