paper-with-me

홈 › Papers

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

2023-05-25 · Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, Anima Anandkumar

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/.

📄 PDF Abstract BibTeX arXiv:2305.16291

Code (1)

MineDojo/Voyager 공식 구현

Tasks

Lifelong learningMinecraft

Methods 이 논문이 사용한 방법론

Library 설명 없음
Multi-Head Attention 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Collaborative Learning

2024-11-20 · Mircea Lică, Ojas Shirekar, Baptiste Colle, Chirag Raman

Contemporary embodied agents, such as Voyager in Minecraft, have demonstrated promising capabilities in open-ended individual learning. However, when powered with open large language models (LLMs), these agents often str…

MinecraftTransfer Learning

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

2024-01-25 · Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu 외

The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents. Existing w…

Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild

2026-03-30 · Deepak Akkil, Mowafak Allaham, Amal Raj, Tamer Abuelsaad 외 arxiv

Reliable evaluation of AI agents operating in complex, real-world environments requires methodologies that are robust, transparent, and contextually aligned with the tasks agents are intended to perform. This study ident…

Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model

2024-04-06 · Zhonghan Zhao, Ke Ma, Wenhao Chai, Xuan Wang 외

With the power of large language models (LLMs), open-ended embodied agents can flexibly understand human instructions, generate interpretable guidance strategies, and output executable actions. Nowadays, Multi-modal Lang…

Knowledge Distillation

Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation

2023-12-12 · Shaopeng Zhai, Jie Wang, Tianyi Zhang, Fuxian Huang 외

Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making fo…

Decision MakingLanguage ModellingReinforcement Learning (RL)