Why Build an Assistant in Minecraft?
By Arthur Szlam, Jonathan Gray, Kavya Srinet, Yacine Jernite, Armand Joulin, Gabriel Synnaeve, Douwe Kiela, Haonan Yu, Zhuoyuan Chen, Siddharth Goyal and 4 more. 2019
32 citations recorded by the source corpus.
In this document we describe a rationale for a research program aimed at building an open "assistant" in the game Minecraft, in order to make progress on the problems of natural language understanding and learning from dialogue.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, LLM Agents & Tool Use
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jason Aaron Edward Weston
- Kurt Shuster
- Y-Lan Boureau
- Eric Michael Smith
- Emily Dinan
- Arthur Szlam
- Stephen Roller
- Da Ju
In Computer Vision and Pattern Recognition
- Jason Aaron Edward Weston
- Kurt Shuster
- Y-Lan Boureau
- Arthur Szlam
- Eric Michael Smith
- Emily Dinan
- Luc Van Gool
- Da Ju
In LLM Agents & Tool Use
Citations in the corpus
- Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, background): “Embodied agents that use language are also being explored (Das et al., 2018; Savva et al., 2019; Szlam et al., 2019; Urbanek et al., 2019).”
- Towards Ecologically Valid Research on Language User Interfaces (2020, unknown): “Popular game environments, like Minecraft (Szlam et al., 2019), could be an excellent platform for developing LUI tasks with high ecological validity.”
- Learning Rewards from Linguistic Feedback (2020, background): “Dialogue systems (Artzi and Zettlemoyer 2011; Li et al. 2016) learn to interpret user queries in the context of the ongoing interaction, while robots and assistants (Thomason et al. 2015; Wang et al. 2019; Thomason et al. 2020; Szlam et al. 2019) ground language in their physical surroundings.”