Learning Efficient Recursive Numeral Systems via Reinforcement Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912381744971776 |
|---|---|
| author | Silvi, Andrea Thomas, Jonathan Carlsson, Emil Dubhashi, Devdatt Johansson, Moa |
| author_facet | Silvi, Andrea Thomas, Jonathan Carlsson, Emil Dubhashi, Devdatt Johansson, Moa |
| contents | It has previously been shown that by using reinforcement learning (RL), agents can derive simple approximate and exact-restricted numeral systems that are similar to human ones (Carlsson, 2021). However, it is a major challenge to show how more complex recursive numeral systems, similar to for example English, could arise via a simple learning mechanism such as RL. Here, we introduce an approach towards deriving a mechanistic explanation of the emergence of efficient recursive number systems. We consider pairs of agents learning how to communicate about numerical quantities through a meta-grammar that can be gradually modified throughout the interactions. Utilising a slightly modified version of the meta-grammar of Hurford (1975), we demonstrate that our RL agents, shaped by the pressures for efficient communication, can effectively modify their lexicon towards Pareto-optimal configurations which are comparable to those observed within human numeral systems in terms of their efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07170 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Efficient Recursive Numeral Systems via Reinforcement Learning Silvi, Andrea Thomas, Jonathan Carlsson, Emil Dubhashi, Devdatt Johansson, Moa Computation and Language It has previously been shown that by using reinforcement learning (RL), agents can derive simple approximate and exact-restricted numeral systems that are similar to human ones (Carlsson, 2021). However, it is a major challenge to show how more complex recursive numeral systems, similar to for example English, could arise via a simple learning mechanism such as RL. Here, we introduce an approach towards deriving a mechanistic explanation of the emergence of efficient recursive number systems. We consider pairs of agents learning how to communicate about numerical quantities through a meta-grammar that can be gradually modified throughout the interactions. Utilising a slightly modified version of the meta-grammar of Hurford (1975), we demonstrate that our RL agents, shaped by the pressures for efficient communication, can effectively modify their lexicon towards Pareto-optimal configurations which are comparable to those observed within human numeral systems in terms of their efficiency. |
| title | Learning Efficient Recursive Numeral Systems via Reinforcement Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.07170 |