Salvato in:
Dettagli Bibliografici
Autori principali: Mangold, Gustavo C., Fernandes, Heitor C. M., Vainstein, Mendeli H.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.02211
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916825339527168
author Mangold, Gustavo C.
Fernandes, Heitor C. M.
Vainstein, Mendeli H.
author_facet Mangold, Gustavo C.
Fernandes, Heitor C. M.
Vainstein, Mendeli H.
contents Recent studies in the spatial prisoner's dilemma games with reinforcement learning have shown that static agents can learn to cooperate through a diverse sort of mechanisms, including noise injection, different types of learning algorithms and neighbours' payoff knowledge. In this work, using an independent multi-agent Q-learning algorithm, we study the effects of dilution and mobility in the spatial version of the prisoner's dilemma. Within this setting, different possible actions for the algorithm are defined, connecting with previous results on the classical, non-reinforcement learning spatial prisoner's dilemma, showcasing the versatility of the algorithm in modeling different game-theoretical scenarios and the benchmarking potential of this approach. As a result, a range of effects is observed, including evidence that games with fixed update rules can be qualitatively equivalent to those with learned ones, as well as the emergence of a symbiotic mutualistic effect between populations that forms when multiple actions are defined.
format Preprint
id arxiv_https___arxiv_org_abs_2507_02211
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dilution, Diffusion and Symbiosis in Spatial Prisoner's Dilemma with Reinforcement Learning
Mangold, Gustavo C.
Fernandes, Heitor C. M.
Vainstein, Mendeli H.
Artificial Intelligence
Neural and Evolutionary Computing
Computational Physics
Recent studies in the spatial prisoner's dilemma games with reinforcement learning have shown that static agents can learn to cooperate through a diverse sort of mechanisms, including noise injection, different types of learning algorithms and neighbours' payoff knowledge. In this work, using an independent multi-agent Q-learning algorithm, we study the effects of dilution and mobility in the spatial version of the prisoner's dilemma. Within this setting, different possible actions for the algorithm are defined, connecting with previous results on the classical, non-reinforcement learning spatial prisoner's dilemma, showcasing the versatility of the algorithm in modeling different game-theoretical scenarios and the benchmarking potential of this approach. As a result, a range of effects is observed, including evidence that games with fixed update rules can be qualitatively equivalent to those with learned ones, as well as the emergence of a symbiotic mutualistic effect between populations that forms when multiple actions are defined.
title Dilution, Diffusion and Symbiosis in Spatial Prisoner's Dilemma with Reinforcement Learning
topic Artificial Intelligence
Neural and Evolutionary Computing
Computational Physics
url https://arxiv.org/abs/2507.02211