Back to AI News
arxiv

Embodied Graph: A Relational World Model for Long-Horizon Tasks

This paper proposes Embodied Graph, a relational state abstraction, and the Relational World Model (RWM) that performs imagination over graph states rather than dense pixel observations. RWM combines a Task-Aware Embodied Graph Constructor that filters redundant details and maintains graph memory, with an Embodied Graph Recurrent State Space Model that learns node-wise latent dynamics and inter-node dependencies. The authors report experiments on Minecraft and Crafter showing effectiveness in embodied environments, noting that RWM is the only method that obtains diamonds within the given budget in Minecraft, and further demonstrate applicability to web agents. The work targets long-horizon planning where delayed feedback and error accumulation make accurate imagination difficult.

AI Brief

It introduces a graph-based world model that improves long-horizon planning in embodied and web environments, with concrete Minecraft and Crafter evaluations.

arXiv:2611.24115v1 Announce Type: new Abstract: Long-horizon tasks in embodied and web environments involve extended decision sequences and delayed feedback, making accurate planning crucial for success. World models tackle this by learning latent dynamics for imagination-based planning. However, existing approaches merely rely on dense pixel-level observations, which forces the model to absorb redundant information while overlooking relations among task-relevant entities. Consequently, small errors may accumulate over long imagined rollouts and gradually corrupt the predictions. In this paper, we explore world models that imagine over sparse state abstractions, which poses two key challenges: 1) how to remove redundant information and form a compact state abstraction; 2) how to incorporate the relational structure to learn reliable long-horizon dynamics. To address these challenges, we propose Embodied Graph, a relational state abstraction that supports structured dynamics modeling and long-horizon imagination, and the Relational World Model (RWM), which performs imagination directly over graph states. RWM consists of (i) a Task-Aware Embodied Graph Constructor that filters redundant details and maintains graph memory through online updates, and (ii) an Embodied Graph Recurrent State Space Model that learns node-wise latent dynamics while capturing inter-node dependencies. The imagined graph states provide predictions of action consequences to guide decision-making. Experiments on Minecraft and Crafter demonstrate the effectiveness of RWM in embodied environments. Notably, in Minecraft, RWM is the only method that obtains diamonds within the given budget. Experiments on web interaction further illustrate the applicability of relational state prediction to the decision making process of web agents.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!