Building spatial world models from sparse transitional episodic memories
This addresses the challenge of building flexible mental models for navigation and planning in animals or AI systems, though it appears incremental as it builds on existing ideas of episodic memory and world models.
The paper tackles the problem of constructing spatial world models from sparse episodic memories, showing that their Episodic Spatial World Model (ESWM) is highly sample-efficient and enables near-optimal exploration and navigation without additional training.
Many animals possess a remarkable capacity to rapidly construct flexible mental models of their environments. These world models are crucial for ethologically relevant behaviors such as navigation, exploration, and planning. The ability to form episodic memories and make inferences based on these sparse experiences is believed to underpin the efficiency and adaptability of these models in the brain. Here, we ask: Can a neural network learn to construct a spatial model of its surroundings from sparse and disjoint episodic memories? We formulate the problem in a simulated world and propose a novel framework, the Episodic Spatial World Model (ESWM), as a potential answer. We show that ESWM is highly sample-efficient, requiring minimal observations to construct a robust representation of the environment. It is also inherently adaptive, allowing for rapid updates when the environment changes. In addition, 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.