Active World Model Learning with Progress Curiosity

• Published in: arXiv.org
• Main Authors: Kuno, Kim, Sano, Megumi, De Freitas, Julian, Haber, Nick, Yamins, Daniel
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 15.07.2020
• Subjects: Distillation; Exploration; Learning; Prediction models; Three dimensional models; White noise

World models are self-supervised predictive models of how the world evolves. Humans learn world models by curiously exploring their environment, in the process acquiring compact abstractions of high bandwidth sensory inputs, the ability to plan across long temporal horizons, and an understanding of...