mlsanityData to 14 Oct 2026

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

arXiv 2512.05335 ↗First posted 5 Dec 2025cs.ROcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

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.

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.

Builds on

21 of 34 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing10 Mar

Other references · 20

  1. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  2. 2014Conditional Generative Adversarial Netscited by 2,162
  3. 2016Generative Adversarial Imitation Learningcited by 1,597
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  5. 2016End to End Learning for Self-Driving Carscited by 1,009
  6. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  7. 2017Wasserstein GANcited by 639
  8. 2019Active Domain Randomizationcited by 170
  9. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 149
  10. 2020Self-Supervised Policy Adaptation during Deploymentcited by 123
  11. 2014Reinforcement and Imitation Learning via Interactive No-Regret Learningcited by 118
  12. 2017Third-Person Imitation Learningcited by 103
8 more
  1. 2017Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstrationcited by 100
  2. 2017Optimization-Based Autonomous Racing of 1:43 Scale RC Carscited by 50
  3. 2018Learning to Drive from Simulation without Real World Labelscited by 39
  4. 2024Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flightcited by 31
  5. 2021Domain Adversarial Reinforcement Learningcited by 19
  6. 2021Invariance Through Latent Alignmentcited by 8
  7. 2022Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agentscited by 7
  8. 2023A Framework for Few-Shot Policy Transfer through Observation Mapping and Behavior Cloningcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Adversarial Imitation Learning from Visual Observations using Latent Information
  2. 2020Domain-Adversarial and Conditional State Space Model for Imitation Learning
  3. 2021Domain-Robust Visual Imitation Learning with Mutual Information Constraints
  4. 2022Imitation Learning by State-Only Distribution Matching
  5. 2018Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning
  6. 2023Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving
  7. 2022Adversarial Imitation Learning from Video using a State Observer
  8. 2026Latent Wasserstein Adversarial Imitation Learning