HackerPapers

arXiv:2305.16291cs.AI

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

Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, Anima Anandkumar

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/.

arXiv comments
Project website and open-source codebase: https://voyager.minedojo.org/
Journal reference
DOI
Subjects
cs.AIArtificial Intelligence cs.LGMachine Learning

On Hacker News

Linked by 5 identifiable commenters in 6 comments across 6 threads, from Aug 2023 to Jan 2026.

Comments linking this paper, per year.

Discussed in comments6 threads

  1. The Code-Only Agent 1 comment

    • sounds like it could be many things. there was a well-known paper called Voyager by NASA in which an agent was able to write its own skills in the form of code and improve them over time. funnily enough this agent played minecraft, and its skills were to collect materials or…

      kbdiazView on HNParent context

  2. Amazon has mostly sat out the AI talent war 1 comment

    • I think LLM as a toolsmith like demonstrated in the Voyager paper (1) is another interesting approach to creating a system that can learn to do a task better over time. (1) https://arxiv.org/abs/2305.16291

      mitjamView on HNParent context

  3. Show HN: Muscle-Mem, a behavior cache for AI agents 1 comment

    • This is very similar to what Voyager did https://arxiv.org/abs/2305.16291 Their implementation uses actual code, JS scripts in their case, as the stored trajectories, which has the neat feature of parameterization built in so trajectories are more reusable. I experimented with…

      eduntemanView on HNParent context

  4. Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking 1 comment

    • > but this is never learned permanently. Are you sure? I think "Open"AI uses the chat transcripts to help the next training run? > they are doomed to only learn what they were pre-trained with Fine-tuning. > The training data for this does not exist What does "this" refer to?…

      exe34View on HNParent context

  5. The AI industry turns against its favorite philosophy 1 comment

    • Cute, there are a number of people and labs working on integrating GPT models with robotics. I think you'd need to train a model on prompt-action pairs to get the best results but you could potentially do what they did in the Voyager paper https://arxiv.org/abs/2305.16291 and…

      throwaway4adayView on HNParent context

  6. OpenAI acquires Global Illumination 1 comment

    • Just dropping this here since it looks like a lot of people haven't heard of it. Voyager: An Open-Ended Embodied Agent with Large Language Models https://arxiv.org/abs/2305.16291

      throwaway4adayView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.