ReCast

ReCast is a reinforcement learning framework for generative recommendation systems, developed by a team of researchers and detailed in an arXiv paper. It focuses on optimizing multi-step user interactions through sequential decision-making.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.