Task-conditioned adaptation of visual features in multi-task policy learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2024

Task-conditioned adaptation of visual features in multi-task policy learning


Successfully addressing a wide variety of tasks is a core ability of autonomous agents, requiring flexibly adapting the underlying decision-making strategies and, as we argue in this work, also adapting the perception modules. An analogical argument would be the human visual system, which uses top-down signals to focus attention determined by the current task. Similarly, we adapt pre-trained large vision models conditioned on specific downstream tasks in the context of multi-task policy learning. We introduce task-conditioned adapters that do not require finetuning any pre-trained weights, combined with a single policy trained with behavior cloning and capable of addressing multiple tasks. We condition the visual adapters on task embeddings, which can be selected at inference if the task is known, or alternatively inferred from a set of example demonstrations. To this end, we propose a new optimization-based estimator. We evaluate the method on a wide variety of tasks from the CortexBench benchmark and show that, compared to existing work, it can be addressed with a single policy. In particular, we demonstrate that adapting visual features is a key design choice and that the method generalizes to unseen tasks given a few demonstrations.
Fichier principal
Vignette du fichier
CVPR2024_Task_Conditioned_Adaptation.pdf (14.76 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04569375 , version 1 (06-05-2024)



  • HAL Id : hal-04569375 , version 1


Pierre Marza, Laetitia Matignon, Olivier Simonin, Christian Wolf. Task-conditioned adaptation of visual features in multi-task policy learning. CVPR 2024 - IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2024, Seattle, United States. pp.1-16. ⟨hal-04569375⟩
0 View
0 Download


Gmail Mastodon Facebook X LinkedIn More