{"id":12940,"date":"2025-12-19T08:40:26","date_gmt":"2025-12-19T08:40:26","guid":{"rendered":"https:\/\/www.yiaho.com\/world-model-in-ai-history-definition-and-explanation\/"},"modified":"2025-12-19T08:40:26","modified_gmt":"2025-12-19T08:40:26","slug":"world-model-in-ai-history-definition-and-explanation","status":"publish","type":"post","link":"https:\/\/www.yiaho.com\/en\/world-model-in-ai-history-definition-and-explanation\/","title":{"rendered":"World Model in AI: History, Definition, and Explanation"},"content":{"rendered":"

World models (or models of the world) represent one of the most promising directions in current artificial intelligence research.<\/p>\n

They aim to equip AI systems with a rich and dynamic internal representation of the environment, capable of predicting the evolution of events, simulating scenarios, and planning actions autonomously.<\/strong><\/p>\n

Unlike purely reactive models, a world model allows AI to “understand” the physical laws, causalities, and uncertainties of the real world. This article, written by the Yiaho team, offers a balanced overview of their history, definition, and operation. <\/p>\n

History of World Models in AI<\/h2>\n

The foundational ideas of world models appeared at the very beginning of AI.<\/p>\n

In the 1950s and 1960s, researchers like Alan Turing<\/a> and Herbert Simon discussed the need for a machine to have an internal representation of its environment to reason effectively.<\/p>\n

The 1970s marked a first concrete realization with symbolic AI: Terry Winograd’s SHRDLU system (1972) manipulated a simplified virtual world of blocks by relying on an explicit modeling of objects and their relationships.<\/p>\n

In the 1980s-1990s, the introduction of probabilistic models (Bayesian networks, hidden Markov models) made it possible to manage uncertainty. These approaches were applied in robotics and planning, particularly for space exploration robots. <\/p>\n

The rise of deep learning<\/a> in the 2010s changed the game. Systems like AlphaGo (DeepMind, 2016) and then MuZero (2020) implicitly learned complex environmental dynamics without manually coded rules. <\/p>\n

The term “world model” became popular in 2018 thanks to the influential work of David Ha and J\u00fcrgen Schmidhuber. Their article “World Models” demonstrated that a neural network<\/a> can learn to compress observations and generate internal simulations, allowing an agent to learn in a “dream” without real interaction. <\/p>\n

Since then, several laboratories have accelerated progress:<\/strong><\/p>\n