A Definition and Roadmap for World Models
Provides a foundational framework for researchers in AI subfields like model-based RL, video generation, and robotics who need a common definition and development path for world models.
This perspective article proposes a scientific definition of world models and outlines a staged roadmap for their development, aiming to unify the fragmented understanding across AI subfields.
World models -- internal simulators that learn the structure and dynamics of an environment -- have become one of the most actively debated concepts in AI. From model-based reinforcement learning and video generation to embodied robotics and ultimately, physical AI, researchers across AI subfields are building systems that they call "world models", yet there is no consensus on what a world model fundamentally is, what it should predict, or how it should be built. This perspective article provides a scientific definition of world models, discussions of their key technical aspects, and a staged roadmap for developing effective world models.