Timezone: »

Active World Model Learning in Agent-rich Environments with Progress Curiosity
Kuno Kim · Megumi Sano · Julian De Freitas · Nick Haber · Daniel Yamins

Thu Jul 16 09:00 AM -- 09:45 AM & Thu Jul 16 11:00 PM -- 11:45 PM (PDT) @
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 and show that $\gamma$-Progress naturally gives rise to an exploration policy that directs attention to complex but learnable dynamics in a balanced manner, as a result overcoming the ``white noise problem''. As a result, our $\gamma$-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.

Author Information

Kuno Kim (Stanford University)
Megumi Sano (Stanford University)
Julian De Freitas (Harvard University)
Nick Haber (Stanford University)

Assistant Professor at Stanford University. Interested in more autonomous, interactively learning AI (e.g. curiosity and self-supervised learning), cognitive models, and learning tools.

Daniel Yamins (Stanford University)

More from the Same Authors