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.
@article{arxiv.2401.00031,
title = {Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges},
author = {Xiaoqian Liu and Jianbin Jiao and Junge Zhang},
journal= {arXiv preprint arXiv:2401.00031},
year = {2024}
}