Mirror Learning

2026-07-30

AI Summary

This work addresses the challenge that existing behavior cloning methods rely on first-person aligned data and struggle to learn effective policies from third-person passive observations. The authors propose a Mirror Learning framework that, for the first time, integrates viewpoint transformation with inverse dynamics modeling. By fine-tuning a video diffusion model to translate third-person observations into first-person perspectives and employing an inverse dynamics model to infer action trajectories, the method generates pseudo-first-person expert demonstrations from purely observational videos. This approach constructs a generative world model capable of training high-performance policies using only mirrored data, substantially reducing reliance on teleoperated demonstrations. When combined with first-person behavior cloning, the framework further enhances downstream policy performance.

Abstract

We investigate imitation learning through the lens of third-person observation and propose a framework for mirror learning: acquiring actionable policies from passive observation. While behavior cloning (BC) excels under dense, well-aligned first-person data, it fundamentally fails to leverage the rich observational signals arising from third-person demonstrations that humans and animals routinely exploit. We introduce a method that composes (i) a learned perspective transformation that places learners in demonstrators' shoes using a fine-tuned video diffusion model and (ii) an inverse dynamics model that infers action trajectories in the learners' control space. This enables the synthesis of mirror data, pseudo first-person expert data generated from third-person observations of demonstrator behavior. Empirically, we show that mirror data alone can train effective policies, and that augmenting first-person BC training with mirror data further improves downstream policy performance. Our results suggest that modern generative world models implicitly encode sufficient structure to enable a scalable and safe alternative to teleoperation-heavy data collection.

Problem

• imitation learning
• third-person observation
• behavior cloning
• mirror learning
• actionable policies

Innovation

• Mirror Learning
• Third-person Imitation
• Video Diffusion Model
• Inverse Dynamics Model
• Behavior Cloning