Consensus-Based Learning for MAS: Definition, Implementation and Integration in IVEs

• C. Carrascosa ^[1] ; F. Enguix ^[1] ; M. Rebollo ^[1] ; J. Rincon ^[1]
  1. [1] Universidad Politécnica de Valencia

     Universidad Politécnica de Valencia

     Valencia, España

     
• Localización: IJIMAI, ISSN-e 1989-1660, Vol. 8, Nº. 3, 2023, págs. 21-32
• Idioma: inglés
• DOI: 10.9781/ijimai.2023.08.004
• Enlaces
  • Texto completo (pdf)
• Resumen

  • One of the main advancements in distributed learning may be the idea behind Google’s Federated Learning (FL) algorithm. It trains copies of artificial neural networks (ANN) in a distributed way and recombines the weights and biases obtained in a central server. Each unit maintains the privacy of the information since the training datasets are not shared. This idea perfectly fits a Multi-Agent System, where the units learning and sharing the model are agents. FL is a centralized approach, where a server is in charge of receiving, averaging and distributing back the models to the different units making the learning process. In this work, we propose a truly distributed learning process where all the agents have the same role in the system. We suggest using a consensus-based learning algorithm that we call Co-Learning. This process uses a consensus process to share the ANN models each agent learns using its private data and calculates the aggregated model. Co-Learning, as a consensus-based algorithm, calculates the average of the ANN models shared by the agents with their local neighbors. This iterative process converges to the averaged ANN model as a central server does. Apart from the definition of the Co-Learning algorithm, the paper presents its integration in SPADE agents, along with a framework called FIVE allowing to develop Intelligent Virtual Environments for SPADE agents. This framework has been used to test the execution of SPADE agents using Co-Learning algorithm in a simulation of an orange orchard field.

• Referencias bibliográficas
  • [1] C. Carrascosa, J. Rincón, M. Rebollo, “Co-learning: Consensus-based learning for multi-agent systems,” in Advances in Practical Applications of...
  • [2] H. Sánchez San Blas, A. Carmona Balea, A. Sales, L. Augusto Silva, G. Villarrubia González, “A platform for swimming pool detection and legal...
  • [3] H. Brendan McMahan, E. Moore, D. Ramage, S. Hampson, B. Agüera y Arcas, “Communication-efficient learning of deep networks from decentralized...
  • [4] P. Kairouz, H. McMahan, B. Avent, A. Bellet, M. Bennis, A. Bhagoji, K. Bonawitz, Z. Charles, G. Cormode, R. Cummings, et al., “Advances...
  • [5] R. Olfati-Saber, R. M. Murray, “Consensus problems in networks of agents with switching topology and time-delays,” IEEE TAC, vol. 49,...
  • [6] J. Palanca, A. Terrasa, V. Julian, C. Carrascosa, “SPADE 3: Supporting the new generation of multi-agent systems,” IEEE Access, vol. 8,...
  • [7] J. Palanca, J. Rincon, V. Julian, C. Carrascosa, A. Terrasa, “Developing iot artifacts in a mas platform,” Electronics, vol. 11, no. 4,...
  • [8] J. Rincon, V. Julian, C. Carrascosa, “Flamas: Federated learning based on a spade mas,” Applied Sciences, vol. 12, no. 7, pp. 1–14, 2022,...
  • [9] M. Bratman, Intention, Plans, and Practical Reason. Cambridge: Cambridge, MA: Harvard University Press, 1987.
  • [10] M. Luck, R. Aylett, “Applying artificial intelligence to virtual reality: Intelligent virtual environments,” Applied artificial intelligence,...
  • [11] A. Ikidid, E. F. Abdelaziz, M. Sadgal, “Multi-agent and fuzzy inferencebased framework for traffic light optimization,” International...
  • [12] U. Wilensky, “Netlogo (and netlogo user manual),” Center for connected learning and computer-based modeling, Northwestern University....
  • [13] J. Rincon, E. Garcia, V. Julian, C. Carrascosa, “The jacalive framework for mas in ive: A case study in evolving modular robotics,” Neurocomputing, vol....
  • [14] A. Barella, A. Ricci, O. Boissier, C. Carrascosa, “Mam5: multi-agent model for intelligent virtual environments,” in 10th european workshop...
  • [15] R. H. Bordini, J. F. Hübner, M. Wooldridge, Programming multi-agent systems in AgentSpeak using Jason. John Wiley & Sons, 2007.
  • [16] A. Ricci, M. Viroli, A. Omicini, “Cartago: A framework for prototyping artifact-based environments in mas,” in International Workshop...
  • [17] S. Luke, G. C. Balan, L. Panait, C. Cioffi-Revilla, S. Paus, “Mason: A java multi-agent simulation library,” in Proceedings of Agent...
  • [18] F. Enguix Andrés, Desarrollo de un generador de simulaciones en Unity 3D para sistemas multi-agente basados en SPADE. PhD dissertation, Universitat...
  • [19] A. Palomares, M. Rebollo, C. Carrascosa, “Supportive consensus,” PLOS ONE, vol. 15, no. 12, pp. 1–30, 2020.
  • [20] F. Pedroche, M. Rebollo, C. Carrascosa, A. Palomares, “Convergence of weighted-average consensus for undirected graphs,” International Journal...
  • [21] J. Palanca, A. Terrasa, V. Julian, C. Carrascosa, “Spade 3: Supporting the new generation of multi-agent systems,” IEEE Access, vol....
  • [22] M. Sandler, A. G. Howard, M. Zhu, A. Zhmoginov, L. Chen, “Inverted residuals and linear bottlenecks: Mobile networks for classification, detection...
  • [23] M. C. Silva, J. C. F. da Silva, R. A. R. Oliveira, “Idissc: Edge-computingbased intelligent diagnosis support system for citrus inspection.,”...