# State-Conditional Adversarial Learning: An Off-Policy Visual Domain Transfer Method for End-to-End Imitation Learning

arXiv: https://arxiv.org/abs/2512.05335 · HTML: https://mlsanity.com/paper/2512.05335/

## 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 21 of its 34 references that are in the map.
- First posted on arXiv 5 Dec 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, 21 of 21)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Active Domain Randomization](https://mlsanity.com/paper/1904.04762/) (2019)
- [DARLA: Improving Zero-Shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/1707.08475/) (2017)
- [Self-Supervised Policy Adaptation during Deployment](https://mlsanity.com/paper/2007.04309/) (2020)
- [Reinforcement and Imitation Learning via Interactive No-Regret Learning](https://mlsanity.com/paper/1406.5979/) (2014)
- [Third-Person Imitation Learning](https://mlsanity.com/paper/1703.01703/) (2017)
- [Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration](https://mlsanity.com/paper/1707.02920/) (2017)
- [Optimization-Based Autonomous Racing of 1:43 Scale RC Cars](https://mlsanity.com/paper/1711.07300/) (2017)
- [Learning to Drive from Simulation without Real World Labels](https://mlsanity.com/paper/1812.03823/) (2018)
- [Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight](https://mlsanity.com/paper/2403.12203/) (2024)
- [Domain Adversarial Reinforcement Learning](https://mlsanity.com/paper/2102.07097/) (2021)
- [Invariance Through Latent Alignment](https://mlsanity.com/paper/2112.08526/) (2021)
- [Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agents](https://mlsanity.com/paper/2201.02569/) (2022)
- [A Framework for Few-Shot Policy Transfer through Observation Mapping and Behavior Cloning](https://mlsanity.com/paper/2310.08836/) (2023)
- [A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing](https://mlsanity.com/paper/2503.07737/) (2025)

## Abstract (arXiv)

We study visual domain transfer for end-to-end imitation learning in a realistic and challenging setting where target-domain data are strictly off-policy, expert-free, and scarce. We first provide a theoretical analysis showing that the target-domain imitation loss can be upper bounded by the source-domain loss plus a state-conditional latent KL divergence between source and target observation models. Guided by this result, we propose State- Conditional Adversarial Learning, an off-policy adversarial framework that aligns latent distributions conditioned on system state using a discriminator-based estimator of the conditional KL term. Experiments on visually diverse autonomous driving environments built on the BARC-CARLA simulator demonstrate that SCAL achieves robust transfer and strong sample efficiency.