Noise-Guided Transport for Imitation Learning
This addresses the problem of data efficiency in imitation learning for robotics and control applications, offering a practical solution for low-data regimes, though it appears incremental as it builds on existing optimal transport and adversarial training concepts.
The paper tackles imitation learning with limited expert demonstrations by introducing Noise-Guided Transport (NGT), a lightweight off-policy method that frames imitation as an optimal transport problem solved via adversarial training, achieving strong performance on challenging continuous control tasks with as few as 20 transitions.
We consider imitation learning in the low-data regime, where only a limited number of expert demonstrations are available. In this setting, methods that rely on large-scale pretraining or high-capacity architectures can be difficult to apply, and efficiency with respect to demonstration data becomes critical. We introduce Noise-Guided Transport (NGT), a lightweight off-policy method that casts imitation as an optimal transport problem solved via adversarial training. NGT requires no pretraining or specialized architectures, incorporates uncertainty estimation by design, and is easy to implement and tune. Despite its simplicity, NGT achieves strong performance on challenging continuous control tasks, including high-dimensional Humanoid tasks, under ultra-low data regimes with as few as 20 transitions. Code is publicly available at: https://github.com/lionelblonde/ngt-pytorch.