A world model is an AI system that learns a predictive representation of how an environment changes over time. It can use observations, actions, or language to estimate future states and possible outcomes before an agent acts. World models support planning in model-based reinforcement learning, robotics, embodied AI, autonomous driving, and interactive simulation. This site catalogs these systems with model records, research papers, benchmark context, and source links. Start with the world models database, compare systems on the leaderboard, or read the Performance Index methodology.
Policy information preserved directly in static HTML.
world-models.io uses a limited set of technical and analytics services to operate the site, understand aggregate usage, prevent abuse, and improve content. Non-essential analytics should be enabled only according to the visitor's consent and applicable law.
The site does not sell personal information. Contact submissions are used to answer the request, investigate corrections, or manage a collaboration. Data is retained only as long as needed for those purposes and may be processed by hosting, email, security, or analytics providers under their service terms.
Visitors may request access, correction, deletion, restriction, portability, or objection where those rights apply. Requests can be sent to contact@world-models.io and should identify the relevant email or interaction without including unnecessary sensitive information.