Towards Human-Agent Communication via the Information Bottleneck
Principle
- URL: http://arxiv.org/abs/2207.00088v1
- Date: Thu, 30 Jun 2022 20:10:20 GMT
- Title: Towards Human-Agent Communication via the Information Bottleneck
Principle
- Authors: Mycal Tucker, Julie Shah, Roger Levy, and Noga Zaslavsky
- Abstract summary: We study how trading off these three factors -- utility, informativeness, and complexity -- shapes emergent communication.
We propose Vector-Quantized Variational Information Bottleneck (VQ-VIB), a method for training neural agents to compress inputs into discrete signals embedded in a continuous space.
- Score: 19.121541894577298
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Emergent communication research often focuses on optimizing task-specific
utility as a driver for communication. However, human languages appear to
evolve under pressure to efficiently compress meanings into communication
signals by optimizing the Information Bottleneck tradeoff between
informativeness and complexity. In this work, we study how trading off these
three factors -- utility, informativeness, and complexity -- shapes emergent
communication, including compared to human communication. To this end, we
propose Vector-Quantized Variational Information Bottleneck (VQ-VIB), a method
for training neural agents to compress inputs into discrete signals embedded in
a continuous space. We train agents via VQ-VIB and compare their performance to
previously proposed neural architectures in grounded environments and in a
Lewis reference game. Across all neural architectures and settings, taking into
account communicative informativeness benefits communication convergence rates,
and penalizing communicative complexity leads to human-like lexicon sizes while
maintaining high utility. Additionally, we find that VQ-VIB outperforms other
discrete communication methods. This work demonstrates how fundamental
principles that are believed to characterize human language evolution may
inform emergent communication in artificial agents.
Related papers
- Learning Multi-Agent Communication with Contrastive Learning [3.816854668079928]
We introduce an alternative perspective where communicative messages are considered as different incomplete views of the environment state.
By examining the relationship between messages sent and received, we propose to learn to communicate using contrastive learning.
In communication-essential environments, our method outperforms previous work in both performance and learning speed.
arXiv Detail & Related papers (2023-07-03T23:51:05Z) - On the Role of Emergent Communication for Social Learning in Multi-Agent
Reinforcement Learning [0.0]
Social learning uses cues from experts to align heterogeneous policies, reduce sample complexity, and solve partially observable tasks.
This paper proposes an unsupervised method based on the information bottleneck to capture both referential complexity and task-specific utility.
arXiv Detail & Related papers (2023-02-28T03:23:27Z) - Less Data, More Knowledge: Building Next Generation Semantic
Communication Networks [180.82142885410238]
We present the first rigorous vision of a scalable end-to-end semantic communication network.
We first discuss how the design of semantic communication networks requires a move from data-driven networks towards knowledge-driven ones.
By using semantic representation and languages, we show that the traditional transmitter and receiver now become a teacher and apprentice.
arXiv Detail & Related papers (2022-11-25T19:03:25Z) - Over-communicate no more: Situated RL agents learn concise communication
protocols [78.28898217947467]
It is unclear how to design artificial agents that can learn to effectively and efficiently communicate with each other.
Much research on communication emergence uses reinforcement learning (RL)
We explore situated communication in a multi-step task, where the acting agent has to forgo an environmental action to communicate.
We find that while all tested pressures can disincentivise over-communication, situated communication does it most effectively and, unlike the cost on effort, does not negatively impact emergence.
arXiv Detail & Related papers (2022-11-02T21:08:14Z) - Neuro-Symbolic Causal Reasoning Meets Signaling Game for Emergent
Semantic Communications [71.63189900803623]
A novel emergent SC system framework is proposed and is composed of a signaling game for emergent language design and a neuro-symbolic (NeSy) artificial intelligence (AI) approach for causal reasoning.
The ESC system is designed to enhance the novel metrics of semantic information, reliability, distortion and similarity.
arXiv Detail & Related papers (2022-10-21T15:33:37Z) - CommsVAE: Learning the brain's macroscale communication dynamics using
coupled sequential VAEs [0.0]
We propose a non-linear generative approach to communication from functional data.
We show that our approach models communication that is more specific to each task.
The specificity of our method means it can have an impact on the understanding of psychiatric disorders.
arXiv Detail & Related papers (2022-10-07T16:20:19Z) - Neuro-Symbolic Artificial Intelligence (AI) for Intent based Semantic
Communication [85.06664206117088]
6G networks must consider semantics and effectiveness (at end-user) of the data transmission.
NeSy AI is proposed as a pillar for learning causal structure behind the observed data.
GFlowNet is leveraged for the first time in a wireless system to learn the probabilistic structure which generates the data.
arXiv Detail & Related papers (2022-05-22T07:11:57Z) - Interpretation of Emergent Communication in Heterogeneous Collaborative
Embodied Agents [83.52684405389445]
We introduce the collaborative multi-object navigation task CoMON.
In this task, an oracle agent has detailed environment information in the form of a map.
It communicates with a navigator agent that perceives the environment visually and is tasked to find a sequence of goals.
We show that the emergent communication can be grounded to the agent observations and the spatial structure of the 3D environment.
arXiv Detail & Related papers (2021-10-12T06:56:11Z) - Learning to cooperate: Emergent communication in multi-agent navigation [49.11609702016523]
We show that agents performing a cooperative navigation task learn an interpretable communication protocol.
An analysis of the agents' policies reveals that emergent signals spatially cluster the state space.
Using populations of agents, we show that the emergent protocol has basic compositional structure.
arXiv Detail & Related papers (2020-04-02T16:03:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.