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

ICLR 2026 Conference Submission18136 Authors

Keywords: Reinforcement Learning, Imitation Learning, Cross-domain Imitation Learning, Imitation from Observation

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 limitation, 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.

Primary Area: reinforcement learning

Submission Number: 18136