+ Site Statistics
+ Search Articles
+ PDF Full Text Service
How our service works
Request PDF Full Text
+ Follow Us
Follow on Facebook
Follow on Twitter
Follow on LinkedIn
+ Subscribe to Site Feeds
Most Shared
PDF Full Text
+ Translate
+ Recently Requested

Emergence of linguistic conventions in multi-agent reinforcement learning

Emergence of linguistic conventions in multi-agent reinforcement learning

Plos one 13(11): E0208095

Recently, emergence of signaling conventions, among which language is a prime example, draws a considerable interdisciplinary interest ranging from game theory, to robotics to evolutionary linguistics. Such a wide spectrum of research is based on much different assumptions and methodologies, but complexity of the problem precludes formulation of a unifying and commonly accepted explanation. We examine formation of signaling conventions in a framework of a multi-agent reinforcement learning model. When the network of interactions between agents is a complete graph or a sufficiently dense random graph, a global consensus is typically reached with the emerging language being a nearly unique object-word mapping or containing some synonyms and homonyms. On finite-dimensional lattices, the model gets trapped in disordered configurations with a local consensus only. Such a trapping can be avoided by introducing a population renewal, which in the presence of superlinear reinforcement restores an ordinary surface-tension driven coarsening and considerably enhances formation of efficient signaling.

Please choose payment method:

(PDF emailed within 0-6 h: $19.90)

Accession: 065772141

Download citation: RISBibTeXText

PMID: 30496267

DOI: 10.1371/journal.pone.0208095

Related references

Effectiveness of reinforcement learning agent with the division of perception information for multi-agent environment. Bulletin of the Okayama University of Science A Natural Science (42A): 115-124, 2006

Multi-agent reinforcement learning: weighting and partitioning. Neural Networks 12(4-5): 727-753, 1999

Optimal control in microgrid using multi-agent reinforcement learning. Isa Transactions 51(6): 743-751, 2012

Embodied imitation-enhanced reinforcement learning in multi-agent systems. Adaptive Behavior 22(1): 31-50, 2014

Collaborative multi-agent reinforcement learning based on experience propagation. Journal of Systems Engineering and Electronics 24(4): 683-689, 2013

Multi-agent reinforcement learning for modeling and control of thermostatically controlled loads. Applied Energy 238: 1022-1035, 2019

Multi-agent discrete-time graphical games and reinforcement learning solutions. Automatica 50(12): 3038-3053, 2014

MARL-Ped: A multi-agent reinforcement learning based framework to simulate pedestrian groups. Simulation Modelling Practice and Theory 47: 259-275, 2014

Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models. Simulation Modelling Practice and Theory 74: 117-133, 2017

Simulation and validation of a reinforcement learning agent-based model for multi-stakeholder forest management. Computers Environment and Urban Systems 34(2): 162-174, 2010

Smart generation control based on multi-agent reinforcement learning with the idea of the time tunnel. Energy 153: 977-987, 2018

A multi-agent reinforcement learning approach to obtaining dynamic control policies for stochastic lot scheduling problem. Simulation Modelling Practice and Theory 13(5): 389-406, 2005

Collision avoidance in multi-robot systems based on multi-layered reinforcement learning. Robotics and Autonomous Systems 29(1): 21-32, 1999

Forward propagating reinforcement learning--biologically plausible learning method for multi-layer networks. Bio Systems 71(1-2): 213-220, 2003

Systematicity, but not compositionality: Examining the emergence of linguistic structure in children and adults using iterated learning. Cognition 181: 160-173, 2018