Critiques of World Models

TL;DR

This paper critiques existing concepts of world models in AI, proposes a new hierarchical, multi-level architecture with generative self-supervised learning, aiming to advance general-purpose, agentic artificial intelligence systems.

Contribution

It offers a critical analysis of current world modeling approaches and introduces a novel hierarchical, mixed-representation architecture with a self-supervised learning framework.

Findings

Proposes a hierarchical, multi-level world model architecture.

Suggests a generative, self-supervised learning framework.

Envisions a Physical, Agentic, and Nested AGI system.

Abstract

World Model, the supposed algorithmic surrogate of the real-world environment which biological agents experience with and act upon, has been an emerging topic in recent years because of the rising needs to develop virtual agents with artificial (general) intelligence. There has been much debate on what a world model really is, how to build it, how to use it, and how to evaluate it. In this essay, starting from the imagination in the famed Sci-Fi classic Dune, and drawing inspiration from the concept of "hypothetical thinking" in psychology literature, we offer critiques of several schools of thoughts on world modeling, and argue the primary goal of a world model to be simulating all actionable possibilities of the real world for purposeful reasoning and acting. Building on the critiques, we propose a new architecture for a general-purpose world model, based on hierarchical, multi-level, and mixed continuous/discrete representations, and a generative and self-supervision learning framework, with an outlook of a Physical, Agentic, and Nested (PAN) AGI system enabled by such a model.