Cross-Domain Imitation Learning with a Dual Structure
On the map: Offline RL and imitation learning from data → Imitation learning methods
Abstract (arXiv)
In this paper, we consider cross-domain imitation learning (CDIL) in which an agent in a target domain learns a policy to perform well in the target domain by observing expert demonstrations in a source domain without accessing any reward function. In order to overcome the domain difference for imitation learning, we propose a dual-structured learning method. The proposed learning method extracts two feature vectors from each input observation such that one vector contains domain information and the other vector contains policy expertness information, and then enhances feature vectors by synthesizing new feature vectors containing both target-domain and policy expertness information. The proposed CDIL method is tested on several MuJoCo tasks where the domain difference is determined by image angles or colors. Numerical results show that the proposed method shows superior performance in CDIL to other existing algorithms and achieves almost the same performance as imitation learning without domain difference.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 22 of its 35 references that are in the map. First posted on arXiv 2 Jun 2020.
Builds on
22 of 35 references.
Closest ancestors · 2
Same direction, newest first
- 2018An Algorithmic Perspective on Imitation Learning16 Nov
- 2018Behavioral Cloning from Observation4 May
Other references · 20
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2016Generative Adversarial Imitation Learningcited by 1,576
- 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
- 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
- 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
- 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
- 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 361
- 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
- 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
- 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
8 more
- 2017Image to Image Translation for Domain Adaptationcited by 171
- 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
- 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 147
- 2018One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learningcited by 146
- 2017Third-Person Imitation Learningcited by 103
- 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 84
- 2018Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translationcited by 50
- 2018Domain Adaptation for Reinforcement Learning on the Ataricited by 5
Built on by
Citing papers per year: 2021: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026Semi-Supervised Cross-Domain Imitation Learning
- 2022Learn what matters: cross-domain imitation learning with task-relevant embeddings
- 2023Domain Adaptive Imitation Learning with Visual Observation
- 2021Cross Domain Robot Imitation with Invariant Representation
- 2021Cross-domain Imitation from Observations
- 2021Cross-Domain Imitation Learning via Optimal Transport
- 2023CEIL: Generalized Contextual Imitation Learning
- 2025Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations