# Domain Adaptive Imitation Learning

arXiv: https://arxiv.org/abs/1910.00105 · HTML: https://mlsanity.com/paper/1910.00105/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 30 Sep 2019.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation](https://mlsanity.com/paper/1707.03374/) (2017)
- [Third-Person Imitation Learning](https://mlsanity.com/paper/1703.01703/) (2017)
- [Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning](https://mlsanity.com/paper/1703.02949/) (2017)
- [Cross-Domain Transfer in Reinforcement Learning using Target Apprentice](https://mlsanity.com/paper/1801.06920/) (2018)

## Built on by (most cited first, 6 of 6)

- [ODRL: A Benchmark for Off-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2410.20750/) (2024)
- [Domain-Robust Visual Imitation Learning with Mutual Information Constraints](https://mlsanity.com/paper/2103.05079/) (2021)
- [Learning from Imperfect Demonstrations via Adversarial Confidence Transfer](https://mlsanity.com/paper/2202.02967/) (2022)
- [Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning](https://mlsanity.com/paper/2106.09256/) (2021)
- [HILONet: Hierarchical Imitation Learning from Non-Aligned Observations](https://mlsanity.com/paper/2011.02671/) (2020)
- [SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring](https://mlsanity.com/paper/2404.03386/) (2024)

## Abstract (arXiv)

We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demonstrations and an additional RL step that requires environment interactions. However, paired, aligned demonstrations are seldom obtainable and RL procedures are expensive. We formalize the Domain Adaptive Imitation Learning (DAIL) problem, which is a unified framework for imitation learning in the presence of viewpoint, embodiment, and dynamics mismatch. Informally, DAIL is the process of learning how to perform a task optimally, given demonstrations of the task in a distinct domain. We propose a two step approach to DAIL: alignment followed by adaptation. In the alignment step we execute a novel unsupervised MDP alignment algorithm, Generative Adversarial MDP Alignment (GAMA), to learn state and action correspondences from unpaired, unaligned demonstrations. In the adaptation step we leverage the correspondences to zero-shot imitate tasks across domains. To describe when DAIL is feasible via alignment and adaptation, we introduce a theory of MDP alignability. We experimentally evaluate GAMA against baselines in embodiment, viewpoint, and dynamics mismatch scenarios where aligned demonstrations don't exist and show the effectiveness of our approach.