Corpus ID: 3340681

Modeling the Formation of Social Conventions in Multi-Agent Populations

  title={Modeling the Formation of Social Conventions in Multi-Agent Populations},
  author={Ismael T. Freire and Cl{\'e}ment Moulin-Frier and M. S{\'a}nchez-Fibla and X. Arsiwalla and P. Verschure},
  • Ismael T. Freire, Clément Moulin-Frier, +2 authors P. Verschure
  • Published 2018
  • Computer Science, Biology, Mathematics
  • ArXiv
  • In order to understand the formation of social conventions we need to know the specific role of control and learning in multi-agent systems. [...] Key Method Our new CRL architecture, as a concrete realization of DAC multi-agent theory, implements a low-level sensorimotor control loop handling the agent's reactive behaviors (pre-wired reflexes), along with a layer based on model-free reinforcement learning that maximizes long-term reward.Expand Abstract
    9 Citations
    Learning Social Conventions in Markov Games
    • 6
    Modeling the Opponent's Action Using Control-Based Reinforcement Learning
    • 2
    • PDF
    Individual Specialization in Multi-Task Environments with Multiagent Reinforcement Learners
    • 1
    • PDF
    Loss Aversion Fosters Coordination in Independent Reinforcement Learners
    • 2
    • PDF
    Policy gradient methods on a multi-agent game with Kullback-Leibler costs
    The Emergence of Social Norms and Conventions
    • 12
    • PDF
    Speeding up Reinforcement Learning by Combining Attention and Agency Features


    A Comprehensive Survey of Multiagent Reinforcement Learning
    • 1,159
    Autonomous development of turn-taking behaviors in agent populations: A computational study
    • 12
    • PDF
    Multiagent cooperation and competition with deep reinforcement learning
    • 277
    • PDF