gComm: An environment for investigating generalization in Grounded Language Acquisition

05/09/2021
by   Rishi Hazra, et al.
0

gComm is a step towards developing a robust platform to foster research in grounded language acquisition in a more challenging and realistic setting. It comprises a 2-d grid environment with a set of agents (a stationary speaker and a mobile listener connected via a communication channel) exposed to a continuous array of tasks in a partially observable setting. The key to solving these tasks lies in agents developing linguistic abilities and utilizing them for efficiently exploring the environment. The speaker and listener have access to information provided in different modalities, i.e. the speaker's input is a natural language instruction that contains the target and task specifications and the listener's input is its grid-view. Each must rely on the other to complete the assigned task, however, the only way they can achieve the same, is to develop and use some form of communication. gComm provides several tools for studying different forms of communication and assessing their generalization.

READ FULL TEXT
research
04/11/2018

Emergent Communication through Negotiation

Multi-agent reinforcement learning offers a way to study how communicati...
research
05/18/2022

Color Overmodification Emerges from Data-Driven Learning and Pragmatic Reasoning

Speakers' referential expressions often depart from communicative ideals...
research
12/08/2022

LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

This study focuses on embodied agents that can follow natural language i...
research
11/10/2016

Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence

Acquiring your first language is an incredible feat and not easily dupli...
research
03/14/2023

CB2: Collaborative Natural Language Interaction Research Platform

CB2 is a multi-agent platform to study collaborative natural language in...
research
03/16/2022

Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching

Natural language processing (NLP) models trained on people-generated dat...
research
12/09/2020

Infinite use of finite means: Zero-Shot Generalization using Compositional Emergent Protocols

Human language has been described as a system that makes use of finite m...

Please sign up or login with your details

Forgot password? Click here to reset