[1703.04908] Emergence of Grounded Compositional Language in Multi-Agent Populations

Abstract:By capturing statistical patterns in large corpora, machine learning has enabled significant advances in natural language processing, including in machine translation, question answering, and sentiment analysis. However, for agents to intelligently interact with humans, simply capturing the statistical patterns is insufficient. In this paper we investigate if, and how, grounded compositional language can emerge as a means to achieve goals in multi-agent populations. Towards this end, we propose a multi-agent learning environment and learning methods that bring about emergence of a basic compositional language. This language is represented as streams of abstract discrete symbols uttered by agents over time, but nonetheless has a coherent structure that possesses a defined vocabulary and syntax. We also observe emergence of non-verbal communication such as pointing and guiding when language communication is unavailable.

Emergence of Grounded Compositional Language in Multi-Agent Populations Igor Mordatch Pieter Abbeel OpenAI UC Berkeley San Francisco, California, USA Berkeley, California, USA Abstract…

saved by

• Sophie Wang

related reading

• [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
• [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
• [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
• [2201.07207] Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentsarxiv.org
• pdfopenreview.net
• [2009.01719] Grounded Language Learning Fast and Slowarxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• [2505.10831] Creating General User Models from Computer Usearxiv.org
• [2309.02427] Cognitive Architectures for Language Agentsarxiv.org
• user_interactions.pdfself-distillation.github.io