• Corpus ID: 214775094

Learning to cooperate: Emergent communication in multi-agent navigation

@article{Kaji2020LearningTC,
  title={Learning to cooperate: Emergent communication in multi-agent navigation},
  author={Ivana Kaji{\'c} and Eser Ayg{\"u}n and Doina Precup},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.01097}
}
Emergent communication in artificial agents has been studied to understand language evolution, as well as to develop artificial systems that learn to communicate with humans. We show that agents performing a cooperative navigation task in various gridworld environments learn an interpretable communication protocol that enables them to efficiently, and in many cases, optimally, solve the task. An analysis of the agents' policies reveals that emergent signals spatially cluster the state space… 

Figures and Tables from this paper

MA-Dreamer: Coordination and communication through shared imagination

TLDR
MA-Dreamer is a model-based method that uses both agent-centric and global differentiable models of the environment in order to train decentralized agents’ policies and critics using model-rollouts a.k.a ‘imagination’ and is compared with other methods on two soccer-based games.

Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation

TLDR
The Evolving Graphical Planner (EGP) is introduced, a model that performs global planning for navigation based on raw sensory input that dynamically constructs a graphical representation, generalizes the action space to allow for more flexible decision making, and performs efficient planning on a proxy graph representation.

Joining the Conversation: Towards Language Acquisition for Ad Hoc Team Play

In this paper, we propose and consider the problem of cooperative language acquisition as a particular form of the ad hoc team play problem. We then present a probabilistic model for inferring a

D ESIGNING N EURAL N ETWORK C OLLECTIVES

TLDR
This work outlines a form of neural network collectives (NNC), motivated by recent work in the field of collective intelligence, and gives details about the specific sub-components that an NNC may have.

S ITUATED COMMUNICATION : A SOLUTION TO OVER COMMUNICATION BETWEEN ARTIFICIAL AGENTS

TLDR
This work introduces situated communication by imposing an opportunity cost on communication—the acting agent has to forgo an action to solicit information from its advisor, and finds that while both pressures can disincentivise over-communication, situated communication does it more effectively and, unlike the internal pressure, does not negatively impact communication emergence.

E MERGENT C OMMUNICATION AT S CALE

TLDR
This work provides a first set of results for large populations solving complex tasks on realistic large-scale datasets, as well as an easy-to-use codebase to enable further experimentation and probes ease-of-learnability and transfer methods to assess emergent languages.

Detecting danger in gridworlds using Gromov's Link Condition

TLDR
A modification to the original Abrams, Ghrist & Peterson setup is introduced to capture agent braiding and thereby more naturally represent the topology of gridworlds, which provides a novel method for seeking guaranteed safety limitations in discrete task environments with single or multiple agents.

Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictability

TLDR
This work focuses on the factors that determine the expressivity of emergent languages, which reflects the amount of information about input spaces those languages are capable of encoding, and measures the expressivities based on the generalisation performance across different games.

Emergent Communication under Varying Group Sizes and Connectivities

TLDR
This research provides an analytical study of the shared emergent language within the group communication settings of different sizes and connectivities and provides optimization results of group communication graphs when the number of agents one can communicate with is restricted or when the authors penalize communication between distant agent pairs.

Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

TLDR
This work proposes an environment and training methodology to serve as a means to carry out an initial exploration of emergent language between agents with a continuous communication channel trained through reinforcement learning, and shows that basic compositionality emerges in the learned language representations.

References

SHOWING 1-10 OF 18 REFERENCES

Young children spontaneously recreate core properties of language in a new modality

TLDR
How young children create new communication systems that exhibit core features of natural languages in less than 30 min are shown, suggesting that children have the basic skills necessary, not only to acquire a natural language, but also to spontaneously create a new one.

Language as shaped by the environment: linguistic construal in a collaborative spatial task

What causes cultural groups to favour specific conventions over others? Recently, it has been suggested that cross-linguistic variation can be motivated by factors of the wider non-linguistic

Ease-of-Teaching and Language Structure from Emergent Communication

TLDR
By introducing new agents periodically to replace old ones, sequentially and within a population, this work explores such a new pressure -- ease of teaching -- and shows its impact on the structure of the resulting language.

Über Sinn und Bedeutung

Die Gleichheit fordert das Nachdenken heraus durch Fragen, die sich daran knupfen und nicht ganz leicht zu beantworten sind. Ist sie eine Beziehung? eine Beziehung zwischen Gegenstanden? oder

CONVENTION: A PHILOSOPHICAL STUDY

On the Pitfalls of Measuring Emergent Communication

TLDR
By training deep reinforcement learning agents to play simple matrix games augmented with a communication channel, this paper finds a scenario where agents appear to communicate, and yet the messages do not impact the environment or other agent in any way.

The Hanabi Challenge: A New Frontier for AI Research

打磨Using Language,倡导新理念

人教版高中英语新课程教材中,语言运用(Using Language)是每个单元必不可少的部分,提供了围绕单元中心话题的听、说、读、写的综合性练习,是单元中心话题的延续和升华.如何设计Using Language部分的教学,使自己的教学模式既不落俗套,又能真正体现新课程标准所倡导的教学理念,正是广大一线英语教师一直努力探索的问题.

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input

TLDR
It is found that the degree of structure found in the input data affects the nature of the emerged protocols, and thereby corroborate the hypothesis that structured compositional language is most likely to emerge when agents perceive the world as being structured.