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 the behavioral patterns of other agents. In this work, we study how to design such a curiosity-driven Active World Model Learning (AWML) system. To do so, we construct a curious agent building world models while visually exploring a 3D physical environment rich with distillations of representative real-world agents. We propose an AWML system driven by $γ$-Progress: a scalable and effective learning progress-based curiosity signal. We show that $γ$-Progress naturally gives rise to an exploration policy that directs attention to complex but learnable dynamics in a balanced manner, thus overcoming the "white noise problem". As a result, our $γ$-Progress-driven controller achieves significantly higher AWML performance than baseline controllers equipped with state-of-the-art exploration strategies such as Random Network Distillation and Model Disagreement.
Curiosity is Knowledge: Self-Consistent Learning and No-Regret Optimization with Active Inference
Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA（航空与宇航系，麻省理工学院）；School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA（工业与系统工程学院，佐治亚理工学院）
Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference
Department of Aeronautics and Astronautics（航空与航天系）；Massachusetts Institute of Technology（麻省理工学院）；School of Industrial and Systems Engineering（工业与系统工程系）；Georgia Institute of Technology（佐治亚理工学院）
Learning to See through Action: Predictive Curiosity for Robots
HERON - Hellenic Robotics Center of Excellence, Athena Research Center（希腊雅典娜研究中心HERON希腊卓越机器人中心）；Institute of Robotics, Athena Research Center（雅典娜研究中心机器人研究所）；National Technical University of Athens, School of Electrical & Computer Engineering（雅典国立技术大学电气与计算机工程学院）
Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries
EPFL（苏黎世联邦理工学院）；ETH Zürich（苏黎世联邦理工学院）；University of Washington（华盛顿大学）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of Michigan（密歇根大学）；MPI for Intelligent Systems, Tübingen, Germany（图宾根智能系统研究所）
Curiosity Driven Exploration to Optimize Structure-Property Learning in Microscopy
Center for Nanophase Materials Sciences, Oak Ridge National Laboratory（纳米相材料科学中心，橡树岭国家实验室）；University of North Carolina（北卡罗来纳大学）；National Cheng Kung University（国立成功大学）；Institute of Science Tokyo（东京科学研究所）；Pacific Northwest National Laboratory（太平洋西北国家实验室）
Active Learning in Physics: From 101, to Progress, and Perspective
University of the Basque Country UPV/EHU（巴斯克大学UPV/EHU）；Shanghai University（上海大学）；Universitat de València（瓦伦西亚大学）；Valencian Graduate School and Research Network of Artificial Intelligence (ValgrAI)（瓦伦西亚人工智能研究生学院与研究网络（ValgrAI））；EHU Quantum Center（EHU量子中心）
