MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control
It is a long-lasting goal to design a generalist-embodied agent that can follow diverse instructions in human-like ways. However, existing approaches often fail to steadily follow instructions due to difficulties in understanding abstract and sequential natural language instructions. To this end, we introduce MineDreamer, an open-ended embodied agent built upon the challenging Minecraft simulator with an innovative paradigm that enhances instruction-following ability in low-level control signal generation. Specifically, MineDreamer is developed on top of recent advances in Multimodal Large Language Models (MLLMs) and diffusion models, and we employ a Chain-of-Imagination (CoI) mechanism to envision the step-by-step process of executing instructions and translating imaginations into more precise visual prompts tailored to the current state; subsequently, the agent generates keyboard-and-mouse actions to efficiently achieve these imaginations, steadily following the instructions at each step. Extensive experiments demonstrate that MineDreamer follows single and multi-step instructions steadily, significantly outperforming the best generalist agent baseline and nearly doubling its performance. Moreover, qualitative analysis of the agent's imaginative ability reveals its generalization and comprehension of the open world.
Code (1)
Tasks
Instruction FollowingMinecraftMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Creative Agents: Empowering Agents with Imagination for Creative Tasks
We study building embodied agents for open-ended creative tasks. While existing methods build instruction-following agents that can perform diverse open-ended tasks, none of them demonstrates creativity -- the ability to…
Instruction FollowingLanguage ModellingLarge Language ModelMinecraftVISTAv2: World Imagination for Indoor Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) requires agents to follow language instructions while acting in continuous real-world spaces. Prior image imagination based VLN work shows benefits for discrete panoramas but lacks on…
Do Visual Imaginations Improve Vision-and-Language Navigation Agents?
Vision-and-Language Navigation (VLN) agents are tasked with navigating an unseen environment using natural language instructions. In this work, we study if visual representations of sub-goals implied by the instructions …
Vision and Language NavigationStimulating Imagination: Towards General-purpose Object Rearrangement
General-purpose object placement is a fundamental capability of an intelligent generalist robot, i.e., being capable of rearranging objects following human instructions even in novel environments. To achieve this, we bre…
ObjectObject LocalizationObject RearrangementPose EstimationChain-of-Instructions: Compositional Instruction Tuning on Large Language Models
Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model's generalization to different tasks, even for unseen tasks. However, most existing instruction datasets …