2021
DOI: 10.48550/arxiv.2110.06536
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment

Julia Kiseleva,
Ziming Li,
Mohammad Aliannejadi
et al.

Abstract: Human intelligence has the remarkable ability to quickly adapt to new tasks and environments. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions. To facilitate research in this direction, we propose IGLU: Interactive Grounded Language Understanding in a Collaborative Environment.The primary goal of the competition is to approach the problem of how to build interactive agents… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
3

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 31 publications
0
3
0
Order By: Relevance
“…Their diversity demonstrates Minecraft's flexibility to both instantiate and evaluate a variety of interesting problems. Research competitions have focused on multi-agent learning of cooperative and competitive tasks (Perez-Liebana et al, 2019), generating functional and believable settlements (Salge et al, 2018), and learning to build structures based on natural language descriptions (Kiseleva et al, 2021). However, none of these competitions are particularly relevant to FTfHF for hard-to-specify sequential decision-making tasks.…”
Section: Rules and Validationmentioning
confidence: 99%
“…Their diversity demonstrates Minecraft's flexibility to both instantiate and evaluate a variety of interesting problems. Research competitions have focused on multi-agent learning of cooperative and competitive tasks (Perez-Liebana et al, 2019), generating functional and believable settlements (Salge et al, 2018), and learning to build structures based on natural language descriptions (Kiseleva et al, 2021). However, none of these competitions are particularly relevant to FTfHF for hard-to-specify sequential decision-making tasks.…”
Section: Rules and Validationmentioning
confidence: 99%
“…A sister competition, MineRL BASALT (Shah et al, 2021), made use of the same MineRL library to express desired agent goals with human demonstrations instead of the rewards, and then used human evaluators to rate the agents on how well they completed the tasks. The IGLU competition (Kiseleva et al, 2021) used the building mechanics of Minecraft for two challenges for the participants: build an agent that provides descriptions on what to build, and then build an agent which builds a structure based on the instructions. Prior to 2021, MarL Ö competition (Perez-Liebana et al, 2019) challenged participants to solve multiple tasks, some unseen, in a multi-agent setting in Minecraft.…”
Section: Related Workmentioning
confidence: 99%
“…Nikolaus and Fourtassi (2021) propose a proof of concept to model perception and production based learning of semantic knowledge acquisition in children. Kiseleva et al (2021) take an interactive approach to language understanding in a recent NeurIPS challenge. To the best of our knowledge, none of the existing works have focused specifically on language modeling.…”
Section: Interactive Language Learning In Nlpmentioning
confidence: 99%