Active World Model Learning With Progress Curiosity

Abstract

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 \(\gamma\)-Progress: a scalable and effective learning progress-based curiosity signal. We show that \(\gamma\)-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 \(\gamma\)-Progress-driven controller ac

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykim2020active

Related papers

• From Curiosity To Competence: How World Models Interact With The Dynamics Of Exploration (2025)0.00
• Foundation World Models For Agents That Learn, Verify, And Adapt Reliably Beyond Static Environments (2026)0.00
• Continual Visual Reinforcement Learning With A Life-long World Model (2023)2.26
• Recurrent World Models Facilitate Policy Evolution (2018)0.00
• What You Think Is What You See: Driving Exploration In VLM Agents Via Visual-linguistic Curiosity (2026)0.00
• Curiosity-driven Exploration Via Latent Bayesian Surprise (2021)0.00
• Enhancing Policy Learning With World-action Model (2026)0.00
• Wonder Wins Ways: Curiosity-driven Exploration Through Multi-agent Contextual Calibration (2025)0.00