paper-with-me

Papers

Simulating the Emergence of Differential Case Marking with Communicating Neural-Network Agents

2025-02-06 · Yuchen Lian, Arianna Bisazza, Tessa Verhoef

Differential Case Marking (DCM) refers to the phenomenon where grammatical case marking is applied selectively based on semantic, pragmatic, or other factors. The emergence of DCM has been studied in artificial language learning experiments with human participants, which were specifically aimed at disentangling the effects of learning from those of communication (Smith & Culbertson, 2020). Multi-agent reinforcement learning frameworks based on neural networks have gained significant interest to simulate the emergence of human-like linguistic phenomena. In this study, we employ such a framework in which agents first acquire an artificial language before engaging in communicative interactions, enabling direct comparisons to human result. Using a very generic communication optimization algorithm and neural-network learners that have no prior experience with language or semantic preferences, our results demonstrate that learning alone does not lead to DCM, but when agents communicate, differential use of markers arises. This supports Smith and Culbertson (2020)'s findings that highlight the critical role of communication in shaping DCM and showcases the potential of neural-agent models to complement experimental research on language evolution.

📄 PDF Abstract BibTeX arXiv:2502.04038

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication

2024-07-19 · Yuchen Lian, Tessa Verhoef, Arianna Bisazza

Recent advances in computational linguistics include simulating the emergence of human-like languages with interacting neural network agents, starting from sets of random symbols. The recently introduced NeLLCom framewor…

Ensuring System-Level Protection against Eavesdropping Adversaries in Distributed Dynamical Systems

2024-09-14 · Dipankar Maity, Van Sy Mai

In this work, we address the objective of protecting the states of a distributed dynamical system from eavesdropping adversaries. We prove that state-of-the-art distributed algorithms, which rely on communicating the age…

Communicating with sentences: A multi-word naming game model

2015-12-28 · Yang Lou, Guanrong Chen, Jianwei Hu

Naming game simulates the process of naming an object by a single word, in which a population of communicating agents can reach global consensus asymptotically through iteratively pair-wise conversations. We propose an e…

Sentence

DAE-PINN: A Physics-Informed Neural Network Model for Simulating Differential-Algebraic Equations with Application to Power Networks

2021-09-09 · Christian Moya, Guang Lin

Deep learning-based surrogate modeling is becoming a promising approach for learning and simulating dynamical systems. Deep-learning methods, however, find very challenging learning stiff dynamics. In this paper, we deve…

Deep Learning

On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating MDPs

2022-09-30 · Yi Wan, Richard S. Sutton

We show two average-reward off-policy control algorithms, Differential Q-learning (Wan, Naik, & Sutton 2021a) and RVI Q-learning (Abounadi Bertsekas & Borkar 2001), converge in weakly communicating MDPs. Weakly communica…

Q-Learning