Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Xiaoqian, Jiao, Jianbin, Zhang, Junge
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2401.00031
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
Table des matières:
  • Decision-making is a dynamic process requiring perception, memory, and reasoning to make choices and find optimal policies. Traditional approaches to decision-making suffer from sample efficiency and generalization, while large-scale self-supervised pretraining has enabled fast adaptation with fine-tuning or few-shot learning in language and vision. We thus argue to integrate knowledge acquired from generic large-scale self-supervised pretraining into downstream decision-making problems. We propose Pretrain-Then-Adapt pipeline and survey recent work on data collection, pretraining objectives and adaptation strategies for decision-making pretraining and downstream inference. Finally, we identify critical challenges and future directions for developing decision foundation model with the help of generic and flexible self-supervised pretraining.