用零散记忆构建灵活空间地图，模拟动物快速导航能力。
Building spatial world models from sparse transitional episodic memories
- 基于离散记忆整合构建空间模型，无需连续轨迹
- 仅靠少量经历就能预测未见路径，潜空间几何匹配环境
- 适合需要快速适应新环境的机器人与强化学习任务
许多动物能迅速构建灵活的认知地图，对导航、探索和规划等行为至关重要。现有计算模型通常需长时间序列数据才能建图，但神经科学证据表明，只需整合符合一致空间规则的离散经验即可形成地图。本文提出一种新的埃皮索德空间世界模型（Episodic Spatial World Model, ESWM），可从稀疏、不连续的事件记忆中构建空间地图。在不同复杂度环境中，ESWM仅凭极少经验就能预测未观测到的转移路径，且其潜在空间结构与真实环境几何高度一致。由于该模型基于可独立存储与更新的事件记忆运行，具备天然的自适应性，能快速响应环境变化。此外，我们证明了ESWM可直接实现接近最优的探索策略和任意点间导航，无需额外训练。本研究展示了如何借鉴神经科学中的情景记忆机制，推动更灵活、通用的世界模型发展。
原文摘要 · Abstract (English)
Many animals possess a remarkable capacity to rapidly construct flexible cognitive maps of their environments. These maps are crucial for ethologically relevant behaviors such as navigation, exploration, and planning. Existing computational models typically require long sequential trajectories to build accurate maps, but neuroscience evidence suggests maps can also arise from integrating disjoint experiences governed by consistent spatial rules. We introduce the Episodic Spatial World Model (ESWM), a novel framework that constructs spatial maps from sparse, disjoint episodic memories. Across environments of varying complexity, ESWM predicts unobserved transitions from minimal experience, and the geometry of its latent space aligns with that of the environment. Because it operates on episodic memories that can be independently stored and updated, ESWM is inherently adaptive, enabling rapid adjustment to environmental changes. Furthermore, we demonstrate that ESWM readily enables near-optimal strategies for exploring novel environments and navigating between arbitrary points, all without the need for additional training. Our work demonstrates how neuroscience-inspired principles of episodic memory can advance the development of more flexible and generalizable world models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。