Training agents to communicate with one another given task-based supervision only has attracted considerable attention recently, due to the growing interest in developing models for human-agent interaction. Prior work on the topic focused on simple environments, where training using policy gradient was feasible despite the non-stationarity of the agents during training. In this paper, we present a more challenging environment for testing the emergence of communication from raw pixels, where training using policy gradient fails. We propose a new model and training algorithm, that utilizes the structure of a learned representation space to produce more consistent speakers at the initial phases of training, which stabilizes learning. We empirically show that our algorithm substantially improves performance compared to policy gradient. We also propose a new alignment-based metric for measuring context-independence in emerged communication and find our method increases context-independence compared to policy gradient and other competitive baselines.
AmarDoctor: An AI-Driven, Multilingual, Voice-Interactive Digital Health Application for Primary Care Triage and Patient Management to Bridge the Digital Health Divide for Bengali Speakers
MedAi Bangladesh Limited(MedAi孟加拉有限公司);Central Police Hospital, Dhaka, Bangladesh(达卡警察医院);University of Birmingham, UK(英国伯明翰大学)
AI Nushu: An Exploration of Language Emergence in Sisterhood -Through the Lens of Computational Linguistics
Royal College of Art(皇家艺术学院);Tsinghua University(清华大学);Politecnico di Milano(米兰理工大学);Hong Kong University of Science and Technology(香港科技大学);Ubisoft(育碧);New Drama Studio(新戏剧工作室);University of London(伦敦大学);King’s College London(伦敦国王学院)
AWED-PIPER: Agents, Web Applications & Expert Detectors for Personally Identifiable Information Protection & Fine-grained Named Entity Recognition across 36 languages for 6.6 Billion Speakers
Indian Institute of Technology Guwahati(印度理工学院古瓦哈蒂分校)