Ethics-Based Cooperation in Multi-agent Systems

Cointe, Nicolas; Bonnet, Grégory; Boissier, Olivier

doi:10.1007/978-3-030-34127-5_10

Cited by 8 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Approaches to multi-agent ethics have also been addressed through various means like introducing morality as a separate explicit consideration that agents balance with their desires, and with heuristics representing responsible multi-agent interactions Cointe et al (2016Cointe et al ( , 2020; Lorini (2012).…”

Section: Open Access Edited Bymentioning

confidence: 99%

Computational Transcendence: Responsibility and agency

Deshmukh

Srinivasa

2022

Front. Robot. AI

View full text Add to dashboard Cite

Emergence of responsible behavior is explored in non-cooperative games involving autonomous agents. Rather than imposing constraints or external reinforcements, agents are endowed with an elastic “sense of self” or an elastic identity that they curate based on rational considerations. This approach is called “computational transcendence (CT).” We show that agents using this model make choices for collective welfare instead of individual benefit. First, relevance of this model in game theoretic contexts like Prisoners’ dilemma and collusion is presented. Next, a generic multi-agent framework for simulating dilemmas around responsible agency is also proposed. CT implemented on this framework, is shown to be versatile in acting responsibly to different kinds of circumstances–including modifying their strategy based on their interaction with other agents in the system as well as interacting with adversaries that are rational maximizers, and who have a rationale to exploit responsible behavior from other agents. CT is also shown to outperform reciprocity as a strategy for responsible autonomy. Thus, we present CT as a framework for building autonomous agents which can intrinsically act responsibly in multi-agent systems. The core model for computational ethics presented in this paper can potentially be adapted to the needs of applications in areas like supply chains, traffic management, and autonomous vehicles. This paper hopes to motivate further research on responsible AI, by exploring computational modeling of this elusive concept called the “sense of self” that is a central element of existential inquiry in humans.

show abstract

Section: Open Access Edited Bymentioning

confidence: 99%

Computational Transcendence: Responsibility and agency

Deshmukh

Srinivasa

2022

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…Os agentes inteligentes são capazes de aprender ou utilizar conhecimentos adquiridos para atingir seus objetivos que podem ser simples ou extremamente complexos [Russell and Norvig 2010]. Segundo [Padgham and Winikoff 2004], um agente inteligente é capaz de responder de maneira oportuna sobre as mudanc ¸as no ambiente e são capazes de executar ac ¸ões para a realizac ¸ão de seu objetivo de forma robusta e flexível [Cointe et al 2020].…”

Section: Agentes Inteligentes (Ai)unclassified

Algoritmos Genéticos aplicado ao mundo de Wumpus: uma comparação entre agentes baseados em regras e agentes inteligentes

Martins¹,

Freitas²,

Mendes³

et al. 2021

Anais Da I Escola Regional De Alto Desempenho Norte 2 (ERAD-ERAMIA-NO2 2021)

View full text Add to dashboard Cite

O presente trabalho compara a aplicação de agentes inteligentes aplicados ao mundo do Wumpus. Os agentes estudados são baseados em regras e algoritmos genéticos (AG). Os experimentos mostram a possibilidade de utilização de ambas técnicas para problemas de busca, bem como um melhor resultado para aquele agente baseado em AG. Além disso, compara variações dos AGs, investigando a utilização de elitismo no processo de seleção da próxima geração.

show abstract

“…Las personas con ética deontológica (conocida como ética de la obligación o del deber) actúan en correspondencia con las normas establecidas. Por otro lado, la ética de la virtud, plantea que una persona es ética, solo si piensa y actúa coherentemente desde los valores morales, cuya actuación debe nacer de manera intrínseca como factor de credibilidad (Cointe, Bonnet, & Boissier, 2016) y (Boissier, Bonnet, Cointe, De Swarte, & Vallée, 2018).…”

Section: Dilemas éTicosunclassified

“…Un grupo de autores Laichter, L. (2019), Yu, H., Shen Z., Miao, C., Leung, C., Lesser, V. & Yang, Q., (2018), Boissier, O., et al, (2018), Varangaonkar, A. (2018), Conitzer, Sinnott, Schaich, Deng & Kramer (2017, Cointe, et al, (2016), coloca la atención en relación con generar alternativas desde la propia tecnología, dedicándose a construir variantes éticas desde esta. Es decir, que el rol de corregir los dilemas se lo otorgan al componente artefactual.…”

Section: Identidadunclassified

See 1 more Smart Citation

Dilemas éticos en el escenario de la inteligencia artificial

Arencibia

Cardero

2020

Econom. y Socied.

View full text Add to dashboard Cite

La importancia del tratamiento del tema asociado a los usos maliciosos de los resultados de la Inteligencia Artificial, está marcando el debate actual de los estudios que se realizan desde las instituciones académicas, por sus implicaciones negativas en el escenario social. En este sentido el propósito de esta investigación, consiste en repensar los dilemas éticos de los desarrollos tecnológicos en el marco de la sociedad digital. Con este propósito la pregunta de investigación es la siguiente: ¿Cómo eliminar los riesgos de un uso malicioso del desarrollo tecnológico en el ámbito de la Inteligencia Artificial? El estudio permite, identificar los puntos críticos que están afectando la sociedad desde las aplicaciones tecnológicas, y promover el debate en torno, a sus soluciones. La conclusión central es que la epistemología para la solución de los dilemas éticos, está por encima de la naturaleza técnica de la Inteligencia Artificial, y exige repensar este fenómeno desde un enfoque multidisciplinario con énfasis en el componente social, observando la práctica de la construcción de los sistemas digitales y sus algoritmos desde un enfoque ético.

show abstract

Ethics-Based Cooperation in Multi-agent Systems

Cited by 8 publications

References 16 publications

Computational Transcendence: Responsibility and agency

Computational Transcendence: Responsibility and agency

Algoritmos Genéticos aplicado ao mundo de Wumpus: uma comparação entre agentes baseados em regras e agentes inteligentes

Dilemas éticos en el escenario de la inteligencia artificial

Contact Info

Product

Resources

About