A promising approach for teaching artificial agents to use natural language involves using human-in-the-loop training. However, recent work suggests that current machine learning methods are too data inefficient to be trained in this way from scratch. In this paper, we investigate the relationship between two categories of learning signals with the ultimate goal of improving sample efficiency: imitating human language data via supervised learning, and maximizing reward in a simulated multi-agent environment via self-play (as done in emergent communication), and introduce the term supervised self-play (S2P) for algorithms using both of these signals. We find that first training agents via supervised learning on human data followed by self-play outperforms the converse, suggesting that it is not beneficial to emerge languages from scratch. We then empirically investigate various S2P schedules that begin with supervised learning in two environments: a Lewis signaling game with symbolic inputs, and an image-based referential game with natural language descriptions. Lastly, we introduce population based approaches to S2P, which further improves the performance over single-agent methods.
NYU（纽约大学）；Robotics at Google（谷歌机器人部门）；Facebook AI Research（脸书人工智能研究院）
In this work, we propose a computational framework in which agents equipped with communication capabilities simultaneously play a series of referential games, where agents are trained using deep reinforcement learning. We demonstrate that the framework mirrors linguistic phenomena observed in natural language: i) the outcome of contact between communities is a function of inter- and intra-group connectivity; ii) linguistic contact either converges to the majority protocol, or in balanced cases leads to novel creole languages of lower complexity; and iii) a linguistic continuum emerges where ne…
Multi-agent reinforcement learning (MARL) has shown recent success in increasingly complex fixed-team zero-sum environments. However, the real world is not zero-sum nor does it have fixed teams; humans face numerous social dilemmas and must learn when to cooperate and when to compete. To successfully deploy agents into the human world, it may be important that they be able to understand and help in our conflicts. Unfortunately, selfish MARL agents typically fail when faced with social dilemmas. In this work, we show evidence of emergent direct reciprocity, indirect reciprocity and reputation, …
Humans use language to collectively execute abstract strategies besides using it as a referential tool for identifying physical entities. Recently, multiple attempts at replicating the process of emergence of language in artificial agents have been made. While existing approaches study emergent languages as referential tools, in this paper, we study their role in discovering and implementing strategies. We formulate the problem using a voting game where two candidate agents contest in an election with the goal of convincing population members (other agents), that are connected to each other vi…
This paper describes a computational model of multiagent multimodal categorization that realizes emergent communication. We clarify whether the computational model can reproduce the following functions in a symbol emergence system, comprising two agents with different sensory modalities playing a naming game. (1) Function for forming a shared lexical system that comprises perceptual categories and corresponding signs, formed by agents through individual learning and semiotic communication between agents. (2) Function to improve the categorization accuracy in an agent via semiotic communication…
We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based training with co-play can lead to a progression in agents' behaviors: from random, to simple ball chasing, and finally showing evidence of cooperation. Our study highlights several of the challenges encountered in large scale multi-agent training in continuous control. In particular, we demonstrate that the automatic optimization of simple shaping rewards, n…
Effective communication is an important skill for enabling information exchange in multi-agent settings and emergent communication is now a vibrant field of research, with common settings involving discrete cheap-talk channels. Since, by definition, these settings involve arbitrary encoding of information, typically they do not allow for the learned protocols to generalize beyond training partners. In contrast, in this work, we present a novel problem setting and the Quasi-Equivalence Discovery (QED) algorithm that allows for zero-shot coordination (ZSC), i.e., discovering protocols that can g…
School of Computer and Artificial Intelligence（计算机与人工智能学院）；Zhengzhou University（郑州大学）
In recent years, human casualties and damage to resources caused by emergent incidents have become a serious problem worldwide. In this paper, we model the emergency decision-making problem and use Multi-agent System (MAS) to solve the problem that the decision speed cannot keep up with the spreading speed. MAS can play an important role in the automated execution of these tasks to reduce mission completion time. In this paper, we propose a P-MADDPG algorithm to solve the emergency decision-making problem of emergent incidents, which predicts the nodes where an incident may occur in the next t…
VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization
Department of Computer Engineering（计算机工程系）；Sharif University of Technology（谢里夫理工学院）；School of Electrical and Computer Engineering（电气与计算机工程学院）；University of Tehran（德黑兰大学）
University of Amsterdam（阿姆斯特丹大学）；Facebook A.I. Research（脸书人工智能研究院）；Universitat Pompeu Fabra（庞培法布拉大学）
To cooperate with humans effectively, virtual agents need to be able to understand and execute language instructions. A typical setup to achieve this is with a scripted teacher which guides a virtual agent using language instructions. However, such setup has clear limitations in scalability and, more importantly, it is not interactive. Here, we introduce an autonomous agent that uses discrete communication to interactively guide other agents to navigate and act on a simulated environment. The developed communication protocol is trainable, emergent and requires no additional supervision. The em…
Facebook AI Research（Facebook人工智能研究院）；ENS - EHESS - PSL Research University - CNRS - INRIA（巴黎高等师范学院-社会科学高等研究院-巴黎文理研究大学-法国国家科学研究中心-法国国家信息与自动化研究所）；ICREA（加泰罗尼亚研究与高等教育学院）
Despite renewed interest in emergent language simulations with neural networks, little is known about the basic properties of the induced code, and how they compare to human language. One fundamental characteristic of the latter, known as Zipf's Law of Abbreviation (ZLA), is that more frequent words are efficiently associated to shorter strings. We study whether the same pattern emerges when two neural networks, a "speaker" and a "listener", are trained to play a signaling game. Surprisingly, we find that networks develop an \emph{anti-efficient} encoding scheme, in which the most frequent inp…
Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
The University of Tokyo（东京大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进情报项目中心）；The Institute of Statistical Mathematics（统计数学研究所）；Google Research Australia（澳大利亚谷歌研究）
Constructive studies on symbol emergence systems seek to investigate computational models that can better explain human language evolution, the creation of symbol systems, and the construction of internal representations. This study provides a new model for emergent communication, which is based on a probabilistic generative model (PGM) instead of a discriminative model based on deep reinforcement learning. We define the Metropolis-Hastings (MH) naming game by generalizing previously proposed models. It is not a referential game with explicit feedback, as assumed by many emergent communication…
The main purpose of relation extraction is to extract the semantic relationships between tagged pairs of entities in a sentence, which plays an important role in the semantic understanding of sentences and the construction of knowledge graphs. In this paper, we propose that the key semantic information within a sentence plays a key role in the relationship extraction of entities. We propose the hypothesis that the key semantic information inside the sentence plays a key role in entity relationship extraction. And based on this hypothesis, we split the sentence into three segments according to …
The drivers of compositionality in artificial languages that emerge when two (or more) agents play a non-visual referential game has been previously investigated using approaches based on the REINFORCE algorithm and the (Neural) Iterated Learning Model. Following the more recent introduction of the \textit{Straight-Through Gumbel-Softmax} (ST-GS) approach, this paper investigates to what extent the drivers of compositionality identified so far in the field apply in the ST-GS context and to what extent do they translate into (emergent) systematic generalisation abilities, when playing a visual …
How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to an increase in reward or task success. This is a useful indicator, but provides only a coarse measure of the agent's learned communication abilities. As we move towards more complex environments, it becomes imperative to have a set of finer tools that allow qualitative and quantitative insights into the emergence of communication. This may be especially useful to allow humans to monitor agents' behaviour, whether for…
Generative statistical models of chord sequences play crucial roles in music processing. To capture syntactic similarities among certain chords (e.g. in C major key, between G and G7 and between F and Dm), we study hidden Markov models and probabilistic context-free grammar models with latent variables describing syntactic categories of chord symbols and their unsupervised learning techniques for inducing the latent grammar from data. Surprisingly, we find that these models often outperform conventional Markov models in predictive power, and the self-emergent categories often correspond to tra…
Massachusetts Institute of Technology（麻省理工学院）；University of Pittsburgh（匹兹堡大学）；Carnegie Mellon University（卡内基梅隆大学）
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do alone. However, the current standard of using one-hot vectors as discrete communication tokens prevents agents from acquiring more desirable aspects of communication such as zero-shot understanding. Inspired by word embedding techniques from natural language processing, we propose neural agent architectures that enables them to communicate via discrete tokens derived from a learned, continuous space. We show in a decis…
We propose a new dataset TexRel as a playground for the study of emergent communications, in particular for relations. By comparison with other relations datasets, TexRel provides rapid training and experimentation, whilst being sufficiently large to avoid overfitting in the context of emergent communications. By comparison with using symbolic inputs, TexRel provides a more realistic alternative whilst remaining efficient and fast to learn. We compare the performance of TexRel with a related relations dataset Shapeworld. We provide baseline performance results on TexRel for sender architecture…
RST-style discourse parsing plays a vital role in many NLP tasks, revealing the underlying semantic/pragmatic structure of potentially complex and diverse documents. Despite its importance, one of the most prevailing limitations in modern day discourse parsing is the lack of large-scale datasets. To overcome the data sparsity issue, distantly supervised approaches from tasks like sentiment analysis and summarization have been recently proposed. Here, we extend this line of research by exploiting distant supervision from topic segmentation, which can arguably provide a strong and oftentimes com…
Emergent LLM behaviors are observationally equivalent to data leakage
Christopher Barrie Assistant Professor of Sociology, New York University（纽约大学社会学助理教授）；New York University（纽约大学）；Petter Törnberg Institute for Logic, Language, and Computation, University of Amsterdam（阿姆斯特丹大学逻辑、语言和计算研究所）；University of Amsterdam（阿姆斯特丹大学）
UCLA（加州大学洛杉矶分校）；Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院）；Peking University（北京大学）
Humans communicate with graphical sketches apart from symbolic languages. Primarily focusing on the latter, recent studies of emergent communication overlook the sketches; they do not account for the evolution process through which symbolic sign systems emerge in the trade-off between iconicity and symbolicity. In this work, we take the very first step to model and simulate this process via two neural agents playing a visual communication game; the sender communicates with the receiver by sketching on a canvas. We devise a novel reinforcement learning method such that agents are evolved jointl…
INRIA（法国国家信息与自动化研究所）；Ecole Normale Supérieure PSL（巴黎高等师范学院PSL）；DeepMind（深度思维）；Google Research（谷歌研究院）；EHESS（社会科学高等学院）；ENS-PSL（巴黎高等师范学院PSL）；CNRS（法国国家科学研究中心）；Meta AI Research（Meta人工智能研究院）
Lewis signaling games are a class of simple communication games for simulating the emergence of language. In these games, two agents must agree on a communication protocol in order to solve a cooperative task. Previous work has shown that agents trained to play this game with reinforcement learning tend to develop languages that display undesirable properties from a linguistic point of view (lack of generalization, lack of compositionality, etc). In this paper, we aim to provide better understanding of this phenomenon by analytically studying the learning problem in Lewis games. As a core cont…
Learning and communication pressures in neural networks: Lessons from emergent communication
Centre for Machine Learning（机器学习中心）；University of Southern Denmark (SDU)（南丹麦大学）；Max Planck Institute for Psycholinguistics（马克斯·普朗克心理语言学研究所）；University of Glasgow（格拉斯哥大学）
