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

Kiseleva, Julia; Li, Ziming; Aliannejadi, Mohammad; Mohanty, Shrestha; ter Hoeve, Maartje; Burtsev, Mikhail; Skrynnik, Alexey; Zholus, Artem; Panov, Aleksandr; Srinet, Kavya; Szlam, Arthur; Sun, Yuxuan; Hofmann, Katja; Galley, Michel; Awadallah, Ahmed

doi:10.48550/arxiv.2110.06536

Cited by 3 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

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%

Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition

Milani¹,

Kanervisto²,

Ramanauskas³

et al. 2023

Preprint

View full text Add to dashboard Cite

To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022. The BASALT challenge asks teams to compete to develop algorithms to solve tasks with hard-to-specify reward functions in Minecraft. Through this competition, we aimed to promote the development of algorithms that use human feedback as channels to learn the desired behavior. We describe the competition and provide an overview of the top solutions. We conclude by discussing the impact of the competition and future directions for improvement.

show abstract

Section: Rules and Validationmentioning

confidence: 99%

Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition

Milani¹,

Kanervisto²,

Ramanauskas³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…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%

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

Kanervisto¹,

Milani²,

Ramanauskas³

et al. 2022

Preprint

View full text Add to dashboard Cite

Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more broadly applicable methods, organizers need to enforce the use of general techniques, the use of sample-efficient methods, and the reproducibility of the results. While beneficial for the research community, these restrictions come at a cost-increased difficulty. If the barrier for entry is too high, many potential participants are demoralized. With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers. With this track and more extensive tutorials and support, we saw an increased number of submissions. The participants of this easier track were able to obtain a diamond, and the participants of the harder track progressed the generalizable solutions in the same task.

show abstract

“…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%

Towards Interactive Language Modeling

Hoeve¹,

Kharitonov²,

Hupkes³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Interaction between caregivers and children plays a critical role in human language acquisition and development. Given this observation, it is remarkable that explicit interaction plays little to no role in artificial language modeling-which also targets the acquisition of human language, yet by artificial models. Moreover, an interactive approach to language modeling has the potential to make language models substantially more versatile and to considerably impact downstream applications. Motivated by these considerations, we pioneer the space of interactive language modeling. As a first contribution we present a road map in which we detail the steps that need to be taken towards interactive language modeling. We then lead by example and take the first steps on this road map, showing the initial feasibility of our approach. As such, this work aims to be the start of a larger research agenda on interactive language modeling.

show abstract

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

Cited by 3 publications

References 31 publications

Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition

Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

Towards Interactive Language Modeling

Contact Info

Product

Resources

About