Voyager: An Open-Ended Embodied Agent with Large Language Models
Indexed inarxivdatacite
Abstract
We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. Voyager interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning. The skills developed by Voyager are temporally extended,…
Citation impact
193
total citations
- FWCI
- —
- Percentile
- —
- References
- 0
Citations per year
Authors
8Topics & keywords
Topics
Keywords
- Codebase
- Computer science
- Executable
- Embodied cognition
- Context (archaeology)
- Key (lock)
- Code (set theory)
- Forgetting
UN Sustainable Development Goals
- Quality Education
No related works found for this paper.