Towards Multi-Agent Communication-Based Language Learning

By Angeliki Lazaridou, Ngoc-Quan Pham, Marco Baroni. 2016

26 citations recorded by the source corpus.

We propose an interactive multimodal framework for language learning. Instead of being passively exposed to large amounts of natural text, our learners (implemented as feed-forward neural networks) engage in cooperative referential games starting from a tabula rasa setup, and thus develop their own language from the need to communicate in order to succeed at the game. Preliminary experiments provide promising results, but also suggest that it is important to ensure that agents trained in this way do not develop an adhoc communication code only effective for the game they are playing

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Emergence of Grounded Compositional Language in Multi-Agent Populations (2017, background): “An interest in pragmatic view of language understanding has been longstanding (Austin 1962; Grice 1975) and has recently argued for in (Gauthier and Mordatch 2016; Lake et al. 2016; Lazaridou, Pham, and Baroni 2016).”
Deep Communicating Agents for Abstractive Summarization (2018, background): “Compared to prior multi-agent works on logic puzzles (Foerster et al., 2017), language learning (Lazaridou et al., 2016; Mordatch and Abbeel, 2017) and starcraft games (Vinyals et al., 2017), we present the ﬁrst study in using this framework for long text generation.”
Zero-Resource Neural Machine Translation with Multi-Agent Communication Game (2018, methodology): “In this work, we introduce a multi-agent communication game within a multimodal environment (Lazaridou, Pham, and Baroni 2016; Havrylov and Titov 2017) to achieve direct modeling of zero-resource source-to-target NMT.”
Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research (2016, background): “Work applying deep reinforcement learning to video games points the way towards agents learning from each other [27, 28, 29].”
Translating Neuralese (2017, background): “DCPs have been shown to solve a variety of coordination problems, including reference games (Lazaridou et al., 2016b), logic puzzles (Foerster et al., 2016), and simple control (Sukhbaatar et al., 2016).”