Emergence of linguistic conventions in multi-agent reinforcement learning.
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 com...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2018-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0208095 |
| _version_ | 1818589044398882816 |
|---|---|
| author | Dorota Lipowska Adam Lipowski |
| author_facet | Dorota Lipowska Adam Lipowski |
| author_sort | Dorota Lipowska |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-16T09:34:23Z |
| format | Article |
| id | doaj.art-6864f26ed59e4b9ca2b34ddfb721a1a0 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-16T09:34:23Z |
| publishDate | 2018-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-6864f26ed59e4b9ca2b34ddfb721a1a02022-12-21T22:36:26ZengPublic Library of Science (PLoS)PLoS ONE1932-62032018-01-011311e020809510.1371/journal.pone.0208095Emergence of linguistic conventions in multi-agent reinforcement learning.Dorota LipowskaAdam LipowskiRecently, 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.https://doi.org/10.1371/journal.pone.0208095 |
| spellingShingle | Dorota Lipowska Adam Lipowski Emergence of linguistic conventions in multi-agent reinforcement learning. PLoS ONE |
| title | Emergence of linguistic conventions in multi-agent reinforcement learning. |
| title_full | Emergence of linguistic conventions in multi-agent reinforcement learning. |
| title_fullStr | Emergence of linguistic conventions in multi-agent reinforcement learning. |
| title_full_unstemmed | Emergence of linguistic conventions in multi-agent reinforcement learning. |
| title_short | Emergence of linguistic conventions in multi-agent reinforcement learning. |
| title_sort | emergence of linguistic conventions in multi agent reinforcement learning |
| url | https://doi.org/10.1371/journal.pone.0208095 |
| work_keys_str_mv | AT dorotalipowska emergenceoflinguisticconventionsinmultiagentreinforcementlearning AT adamlipowski emergenceoflinguisticconventionsinmultiagentreinforcementlearning |