Um estudo sobre sistemas multiagentes e a categorização de diferentes níveis para a transferência de conhecimento
Resumo
Este artigo apresenta uma análise sobre agentes, sistemas multiagentes, transferência de conhecimento e técnicas para a transferência. Propõem-se a classificação de diferentes tipos de transferência, separadas em camadas para o nível de agentes, organizações e sociedades, investigando como políticas para a realização de tarefas por agentes são compreendidas na literatura.Referências
Demazeau, Y. (1995). From interactions to collective behaviour in agent-based systems. In In: Proceedings of the 1st. European Conference on Cognitive Science. Saint-Malo. Citeseer.
Grover, A., Al-Shedivat, M., Gupta, J., Burda, Y., and Edwards, H. (2018). Learning policy representations in multiagent systems. In International conference on machine learning, pages 1802–1811. PMLR.
Huhns, M. N. and Stephens, L. M. (1999). Multiagent systems and societies of agents. Multiagent systems: a modern approach to distributed artificial intelligence, 1:79–114.
Lesser, V. R. (1999). Cooperative multiagent systems: A personal view of the state of the art. IEEE Transactions on knowledge and data engineering, 11(1):133–142.
Liang, Y. and Li, B. (2020). Parallel knowledge transfer in multi-agent reinforcement learning. arXiv preprint arXiv:2003.13085.
McArthur, S. D., Davidson, E. M., Catterson, V. M., Dimeas, A. L., Hatziargyriou, N. D., Ponci, F., and Funabashi, T. (2007). Multi-agent systems for power engineering applications—part i: Concepts, approaches, and technical challenges. IEEE Transactions on Power systems, 22(4):1743–1752.
Newell, A. et al. (1982). The knowledge level. Artificial intelligence, 18(1):87–127.
Shoham, Y. and Tennenholtz, M. (1995). On social laws for artificial agent societies: Off-line design. Artificial intelligence, 73(1-2):231–252.
Silva, F. (2019). Methods and Algorithms for Knowledge Reuse in Multiagent Reinforcement Learning. PhD thesis.
Takadama, K., Terano, T., and Shimohara, K. (2000). Which organizational knowledge is useful: rare, medium, or well-done?-comparison of different levels of organizational knowledge in multiagent environments. In 2000 26th Annual Conference of the IEEE Industrial Electronics Society. IECON 2000. 2000 IEEE International Conference on Industrial Electronics, Control and Instrumentation. 21st Century Technologies, volume 4, pages 2891–2896. IEEE.
Taylor, M. E., Kuhlmann, G., and Stone, P. (2008). Autonomous transfer for reinforcement learning. In AAMAS (1), pages 283–290.
Tuyls, K. and Stone, P. (2017). Multiagent learning paradigms. In Multi-Agent Systems and Agreement Technologies, pages 3–21. Springer.
Grover, A., Al-Shedivat, M., Gupta, J., Burda, Y., and Edwards, H. (2018). Learning policy representations in multiagent systems. In International conference on machine learning, pages 1802–1811. PMLR.
Huhns, M. N. and Stephens, L. M. (1999). Multiagent systems and societies of agents. Multiagent systems: a modern approach to distributed artificial intelligence, 1:79–114.
Lesser, V. R. (1999). Cooperative multiagent systems: A personal view of the state of the art. IEEE Transactions on knowledge and data engineering, 11(1):133–142.
Liang, Y. and Li, B. (2020). Parallel knowledge transfer in multi-agent reinforcement learning. arXiv preprint arXiv:2003.13085.
McArthur, S. D., Davidson, E. M., Catterson, V. M., Dimeas, A. L., Hatziargyriou, N. D., Ponci, F., and Funabashi, T. (2007). Multi-agent systems for power engineering applications—part i: Concepts, approaches, and technical challenges. IEEE Transactions on Power systems, 22(4):1743–1752.
Newell, A. et al. (1982). The knowledge level. Artificial intelligence, 18(1):87–127.
Shoham, Y. and Tennenholtz, M. (1995). On social laws for artificial agent societies: Off-line design. Artificial intelligence, 73(1-2):231–252.
Silva, F. (2019). Methods and Algorithms for Knowledge Reuse in Multiagent Reinforcement Learning. PhD thesis.
Takadama, K., Terano, T., and Shimohara, K. (2000). Which organizational knowledge is useful: rare, medium, or well-done?-comparison of different levels of organizational knowledge in multiagent environments. In 2000 26th Annual Conference of the IEEE Industrial Electronics Society. IECON 2000. 2000 IEEE International Conference on Industrial Electronics, Control and Instrumentation. 21st Century Technologies, volume 4, pages 2891–2896. IEEE.
Taylor, M. E., Kuhlmann, G., and Stone, P. (2008). Autonomous transfer for reinforcement learning. In AAMAS (1), pages 283–290.
Tuyls, K. and Stone, P. (2017). Multiagent learning paradigms. In Multi-Agent Systems and Agreement Technologies, pages 3–21. Springer.
Publicado
10/08/2021
Como Citar
RODRIGUES, Paulo Felipe G. L.; ADAMATTI, Diana F.; GONÇALVES, Eder Mateus N..
Um estudo sobre sistemas multiagentes e a categorização de diferentes níveis para a transferência de conhecimento. In: WORKSHOP-ESCOLA DE SISTEMAS DE AGENTES, SEUS AMBIENTES E APLICAÇÕES (WESAAC), 15. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 143-147.
ISSN 2326-5434.
