论文标题
一个受生物学启发的双流世界模型
A Biologically-Inspired Dual Stream World Model
论文作者
论文摘要
内侧颞叶（MTL）是一个包含海马和附近区域的大脑区域，被认为是哺乳动物的体验构造系统，支持暂时扩展的事件序列的回忆和想象。此类功能也是许多最近提出的AI研究领域中``世界模型''的核心。从这种联系中汲取灵感，我们提出了一种新颖的变体，双流世界模型（DSWM），从高维观察中学习，从高维观察中学习，并将它们分离为上下文和内容流中。dswm仅在新颖的世界中提供了一个单身的启动。还学习潜在表示，与在海马中发现的细胞相似，我们表明该表示形式可作为增强学习基础功能，并且可以使用生成模型来帮助使用类似Dyna的更新来帮助策略学习过程。
The medial temporal lobe (MTL), a brain region containing the hippocampus and nearby areas, is hypothesized to be an experience-construction system in mammals, supporting both recall and imagination of temporally-extended sequences of events. Such capabilities are also core to many recently proposed ``world models" in the field of AI research. Taking inspiration from this connection, we propose a novel variant, the Dual Stream World Model (DSWM), which learns from high-dimensional observations and dissociates them into context and content streams. DSWM can reliably generate imagined trajectories in novel 2D environments after only a single exposure, outperforming a standard world model. DSWM also learns latent representations which bear a strong resemblance to place cells found in the hippocampus. We show that this representation is useful as a reinforcement learning basis function, and that the generative model can be used to aid the policy learning process using Dyna-like updates.
