Building collaboration in multi-agent systems using reinforcement learning

Aydin M. E., Fellows R.

10th International Conference on Computational Collective Intelligence, ICCCI 2018, Bristol, İngiltere, 5 - 07 Eylül 2018, cilt.11056 LNAI, ss.201-212, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 11056 LNAI
  • Doi Numarası: 10.1007/978-3-319-98446-9_19
  • Basıldığı Şehir: Bristol
  • Basıldığı Ülke: İngiltere
  • Sayfa Sayıları: ss.201-212
  • Anahtar Kelimeler: Agent collaboration, Disaster management, Multi-agent systems, Q learning, Reinforcement learning
  • İstanbul Ticaret Üniversitesi Adresli: Hayır

Özet

This paper presents a proof-of concept study for demonstrating the viability of building collaboration among multiple agents through standard Q learning algorithm embedded in particle swarm optimisation. Collaboration is formulated to be achieved among the agents via competition, where the agents are expected to balance their action in such a way that none of them drifts away of the team and none intervene any fellow neighbours territory, either. Particles are devised with Q learning for self training to learn how to act as members of a swarm and how to produce collaborative/collective behaviours. The produced experimental results are supportive to the proposed idea suggesting that a substantive collaboration can be build via proposed learning algorithm.