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

arXiv: https://arxiv.org/abs/2502.02867 · HTML: https://mlsanity.com/paper/2502.02867/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 13 of its 83 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 13 of 13)

- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Efficient Exploration via State Marginal Matching](https://mlsanity.com/paper/1906.05274/) (2019)
- [Generative Adversarial Imitation from Observation](https://mlsanity.com/paper/1807.06158/) (2018)
- [Primal Wasserstein Imitation Learning](https://mlsanity.com/paper/2006.04678/) (2020)
- [Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow](https://mlsanity.com/paper/1810.00821/) (2018)
- [Domain-Robust Visual Imitation Learning with Mutual Information Constraints](https://mlsanity.com/paper/2103.05079/) (2021)
- [IL-flOw: Imitation Learning from Observation using Normalizing Flows](https://mlsanity.com/paper/2205.09251/) (2022)
- [OIL: Observational Imitation Learning](https://mlsanity.com/paper/1803.01129/) (2018)
- [Imitation Learning from Observations under Transition Model Disparity](https://mlsanity.com/paper/2204.11446/) (2022)
- [Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching](https://mlsanity.com/paper/2311.01331/) (2023)

## Abstract (arXiv)

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.