paper-with-me

홈 › Papers

CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter

2025-08-19 · Junyeong Park, Hyeonseo Cho, Sungjin Ahn arxiv

Developing general-purpose embodied agents is a core challenge in AI. Minecraft provides rich complexity and internet-scale data, but its slow speed and engineering overhead make it unsuitable for rapid prototyping. Crafter offers a lightweight alternative that retains key challenges from Minecraft, yet its use has remained limited to narrow tasks due to the absence of foundation models that have driven progress in the Minecraft setting. In this paper, we present CrafterDojo, a suite of foundation models and tools that unlock the Crafter environment as a lightweight, prototyping-friendly, and Minecraft-like testbed for general-purpose embodied agent research. CrafterDojo addresses this by introducing CrafterVPT, CrafterCLIP, and CrafterSteve-1 for behavior priors, vision-language grounding, and instruction following, respectively. In addition, we provide toolkits for generating behavior and caption datasets (CrafterPlay and CrafterCaption), reference agent implementations, benchmark evaluations, and a complete open-source codebase.

📄 PDF Abstract BibTeX arXiv:2508.13530

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction Following

Similar Papers 제목 키워드 기반

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge

2022-06-17 · Linxi Fan, Guanzhi Wang, Yunfan Jiang, Ajay Mandlekar 외

Autonomous agents have made great strides in specialist domains like Atari games and Go. However, they typically learn tabula rasa in isolated environments with limited and manually conceived objectives, thus failing to …

Atari GamesMinecraft

Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

2024-11-21 · Yu Zhao, Huifeng Yin, Bo Zeng, Hao Wang 외

Currently OpenAI o1 sparks a surge of interest in the study of large reasoning models (LRM). Building on this momentum, Marco-o1 not only focuses on disciplines with standard answers, such as mathematics, physics, and co…

Reinforcement Learning (RL)

Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning

2022-07-25 · Deborah Cohen, MoonKyung Ryu, Yinlam Chow, Orgad Keller 외

Despite recent advances in natural language understanding and generation, and decades of research on the development of conversational bots, building automated agents that can carry on rich open-ended conversations with …

Natural Language Understandingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset

2026-04-24 · Wenhui Huang, Songyan Zhang, Collister Chua, Yang Liang 외 arxiv

Urban transportation systems face growing safety challenges that require scalable intelligence for emerging smart mobility infrastructures. While recent advances in foundation models and large-scale multimodal datasets h…

Visual Question AnsweringAutonomous Driving

Open-Endedness is Essential for Artificial Superhuman Intelligence

2024-06-06 · Edward Hughes, Michael Dennis, Jack Parker-Holder, Feryal Behbahani 외

In recent years there has been a tremendous surge in the general capabilities of AI systems, mainly fuelled by training foundation models on internetscale data. Nevertheless, the creation of openended, ever self-improvin…