Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations

TL;DR

This paper introduces DIFF-IL, a novel imitation learning method that extracts domain-invariant features from individual frames and uses temporal labeling to improve cross-domain visual imitation tasks.

Contribution

The paper proposes a new IL approach that isolates domain-invariant features per frame and employs frame-wise time labeling for better behavior segmentation and reward assignment.

Findings

DIFF-IL outperforms existing methods in diverse visual environments.

Effective in handling high-dimensional, noisy, and incomplete visual observations.

Improves imitation learning performance across different visual domains.

Abstract

Imitation learning (IL) enables agents to mimic expert behavior without reward signals but faces challenges in cross-domain scenarios with high-dimensional, noisy, and incomplete visual observations. To address this, we propose Domain-Invariant Per-Frame Feature Extraction for Imitation Learning (DIFF-IL), a novel IL method that extracts domain-invariant features from individual frames and adapts them into sequences to isolate and replicate expert behaviors. We also introduce a frame-wise time labeling technique to segment expert behaviors by timesteps and assign rewards aligned with temporal contexts, enhancing task performance. Experiments across diverse visual environments demonstrate the effectiveness of DIFF-IL in addressing complex visual tasks.