PhilSci Archive

Compositional Understanding in Signaling Games

Freeborn, David Peter Wallis (2025) Compositional Understanding in Signaling Games. [Preprint]

[img] Text
Compositional_Signals_Freeborn.pdf

Download (1MB)

Abstract

Receivers in standard signaling game models struggle with learning compositional information. Even when the signalers send compositional messages, the receivers do not interpret them compositionally. When information from one message component is lost or forgotten, the information from other components is also erased. In this paper I construct signaling game models in which genuine compositional understanding evolves. I present two new models: a minimalist receiver who only learns from the atomic messages of a signal, and a generalist receiver who learns from all of the available information. These models are in many ways simpler than previous alternatives, and allow the receivers to learn from the atomic components of messages.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Freeborn, David Peter Wallisdfreebor@uci.edu0000-0002-2117-8145
Keywords: signaling games; signalling games; signaling; signalling; compositionality; Game Theory; evolutionary game theory; Language; Communication; Philosophy of Science; philosophy of game theory; naturalised models; computational models; naturalised philosophy; neural networks; signals; evolution of language; Philosophy of language; Semantics; artificial intelligence; philosophy of A.I; philosophy of artificial intelligence
Subjects: Specific Sciences > Biology > Evolutionary Theory
Specific Sciences > Computation/Information
Specific Sciences > Artificial Intelligence
General Issues > Computer Simulation
General Issues > Game Theory
Specific Sciences > Cognitive Science > Learning and Memory
Specific Sciences > Artificial Intelligence > Machine Learning
Depositing User: David Freeborn
Date Deposited: 23 Jul 2025 16:59
Last Modified: 23 Jul 2025 16:59
Item ID: 26003
Subjects: Specific Sciences > Biology > Evolutionary Theory
Specific Sciences > Computation/Information
Specific Sciences > Artificial Intelligence
General Issues > Computer Simulation
General Issues > Game Theory
Specific Sciences > Cognitive Science > Learning and Memory
Specific Sciences > Artificial Intelligence > Machine Learning
Date: 21 July 2025
URI: https://philsci-archive.pitt.edu/id/eprint/26003

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item