Active Fine-Tuning of Multi-Task Policies

Marco Bagatella, Jonas Hübotter, Georg Martius, Andreas Krause
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2409-2441, 2025.

Abstract

Pre-trained generalist policies are rapidly gaining relevance in robot learning due to their promise of fast adaptation to novel, in-domain tasks. This adaptation often relies on collecting new demonstrations for a specific task of interest and applying imitation learning algorithms, such as behavioral cloning. However, as soon as several tasks need to be learned, we must decide which tasks should be demonstrated and how often? We study this multi-task problem and explore an interactive framework in which the agent adaptively selects the tasks to be demonstrated. We propose AMF (Active Multi-task Fine-tuning), an algorithm to maximize multi-task policy performance under a limited demonstration budget by collecting demonstrations yielding the largest information gain on the expert policy. We derive performance guarantees for AMF under regularity assumptions and demonstrate its empirical effectiveness to efficiently fine-tune neural policies in complex and high-dimensional environments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-bagatella25a, title = {Active Fine-Tuning of Multi-Task Policies}, author = {Bagatella, Marco and H\"{u}botter, Jonas and Martius, Georg and Krause, Andreas}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {2409--2441}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/bagatella25a/bagatella25a.pdf}, url = {https://proceedings.mlr.press/v267/bagatella25a.html}, abstract = {Pre-trained generalist policies are rapidly gaining relevance in robot learning due to their promise of fast adaptation to novel, in-domain tasks. This adaptation often relies on collecting new demonstrations for a specific task of interest and applying imitation learning algorithms, such as behavioral cloning. However, as soon as several tasks need to be learned, we must decide which tasks should be demonstrated and how often? We study this multi-task problem and explore an interactive framework in which the agent adaptively selects the tasks to be demonstrated. We propose AMF (Active Multi-task Fine-tuning), an algorithm to maximize multi-task policy performance under a limited demonstration budget by collecting demonstrations yielding the largest information gain on the expert policy. We derive performance guarantees for AMF under regularity assumptions and demonstrate its empirical effectiveness to efficiently fine-tune neural policies in complex and high-dimensional environments.} }
Endnote
%0 Conference Paper %T Active Fine-Tuning of Multi-Task Policies %A Marco Bagatella %A Jonas Hübotter %A Georg Martius %A Andreas Krause %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-bagatella25a %I PMLR %P 2409--2441 %U https://proceedings.mlr.press/v267/bagatella25a.html %V 267 %X Pre-trained generalist policies are rapidly gaining relevance in robot learning due to their promise of fast adaptation to novel, in-domain tasks. This adaptation often relies on collecting new demonstrations for a specific task of interest and applying imitation learning algorithms, such as behavioral cloning. However, as soon as several tasks need to be learned, we must decide which tasks should be demonstrated and how often? We study this multi-task problem and explore an interactive framework in which the agent adaptively selects the tasks to be demonstrated. We propose AMF (Active Multi-task Fine-tuning), an algorithm to maximize multi-task policy performance under a limited demonstration budget by collecting demonstrations yielding the largest information gain on the expert policy. We derive performance guarantees for AMF under regularity assumptions and demonstrate its empirical effectiveness to efficiently fine-tune neural policies in complex and high-dimensional environments.
APA
Bagatella, M., Hübotter, J., Martius, G. & Krause, A.. (2025). Active Fine-Tuning of Multi-Task Policies. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:2409-2441 Available from https://proceedings.mlr.press/v267/bagatella25a.html.

Related Material