Constrained Style Learning from Imperfect Demonstrations under Task Optimality

TL;DR

This paper introduces a constrained learning framework that enables robots to imitate style from imperfect demonstrations while maintaining near-optimal task performance, validated on real robotic hardware.

Contribution

It formulates style learning as a constrained Markov Decision Process with an adaptive Lagrangian, allowing selective imitation without sacrificing task effectiveness.

Findings

Achieved high-fidelity style imitation on multiple robots.

Maintained near-optimal task performance despite imperfect demonstrations.

Reduced mechanical energy by 14.5% on real hardware.

Abstract

Learning from demonstration has proven effective in robotics for acquiring natural behaviors, such as stylistic motions and lifelike agility, particularly when explicitly defining style-oriented reward functions is challenging. Synthesizing stylistic motions for real-world tasks usually requires balancing task performance and imitation quality. Existing methods generally depend on expert demonstrations closely aligned with task objectives. However, practical demonstrations are often incomplete or unrealistic, causing current methods to boost style at the expense of task performance. To address this issue, we propose formulating the problem as a constrained Markov Decision Process (CMDP). Specifically, we optimize a style-imitation objective with constraints to maintain near-optimal task performance. We introduce an adaptively adjustable Lagrangian multiplier to guide the agent to imitate demonstrations selectively, capturing stylistic nuances without compromising task performance. We validate our approach across multiple robotic platforms and tasks, demonstrating both robust task performance and high-fidelity style learning. On ANYmal-D hardware we show a 14.5% drop in mechanical energy and a more agile gait pattern, showcasing real-world benefits.