Multi-Agent Cooperation and the Emergence of (Natural) Language

Abstract

The current mainstream approach to train natural language systems is to expose them to large amounts of text. This passive learning is problematic if we are interested in developing interactive machines, such as conversational agents. We propose a framework for language learning that relies on multi-agent communication. We study this learning in the context of referential games. In these games, a sender and a receiver see a pair of images. The sender is told one of them is the target and is allowed to send a message from a fixed, arbitrary vocabulary to the receiver. The receiver must rely on this message to identify the target. Thus, the agents develop their own language interactively out of the need to communicate. We show that two networks with simple configurations are able to learn to coordinate in the referential game. We further explore how to make changes to the game environment to cause the "word meanings" induced in the game to better reflect intuitive semantic properties of the images. In addition, we present a simple strategy for grounding the agents' code into natural language. Both of these are necessary steps towards developing machines that are able to communicate with humans productively.

Accepted at ICLR 2017

Cited by in corpus (10)

• RODE: Learning Roles to Decompose Multi-Agent Tasks
• Off-Policy Multi-Agent Decomposed Policy Gradients
• Emergent Multi-Agent Communication in the Deep Learning Era
• Measuring Compositionality in Representation Learning
• Avoiding hashing and encouraging visual semantics in referential emergent language games
• Modeling Conceptual Understanding in Image Reference Games
• Symbol Emergence as an Interpersonal Multimodal Categorization
• Towards Graph Representation Learning in Emergent Communication
• Paying Attention to Function Words
• Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game