Voyager: An Open-Ended Embodied Agent with Large Language Models

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, interpretable, and compositional, which compounds the agent's abilities rapidly and alleviates catastrophic forgetting. Empirically, Voyager shows strong in-context lifelong learning capability and exhibits exceptional proficiency in playing Minecraft. It obtains 3.3x more unique items, travels 2.3x longer distances, and unlocks key tech tree milestones up to 15.3x faster than prior SOTA. Voyager is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch, while other techniques struggle to generalize. We open-source our full codebase and prompts at https://voyager.minedojo.org/.

Project website and open-source codebase: https://voyager.minedojo.org/

Cited by in corpus (19)

• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
• A GPT-4 Reticular Chemist for Guiding MOF Discovery
• Theory of Mind for Multi-Agent Collaboration via Large Language Models
• Anatomy of an AI-powered malicious social botnet
• From Intention To Implementation: Automating Biomedical Research via LLMs
• Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art
• Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models
• Domain-specific ChatBots for Science using Embeddings
• Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
• Agents for self-driving laboratories applied to quantum computing
• Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering
• Adaptive Intelligence: leveraging insights from adaptive behavior in animals to build flexible AI systems
• Bootstrapping Cognitive Agents with a Large Language Model
• Developmental Scaffolding with Large Language Models
• AgentArcEval: An Architecture Evaluation Method for Foundation Model based Agents
• Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study
• Medical Vision Language Models as Policies for Robotic Surgery
• A Hormetic Approach to the Value-Loading Problem: Preventing the Paperclip Apocalypse?
• Tool-Augmented LLMs as a Universal Interface for IDEs