Saved in:
Bibliographic Details
Main Authors: Liu, Xiaoqian, Jiao, Jianbin, Zhang, Junge
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2401.00031
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909062423117824
author Liu, Xiaoqian
Jiao, Jianbin
Zhang, Junge
author_facet Liu, Xiaoqian
Jiao, Jianbin
Zhang, Junge
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_00031
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges
Liu, Xiaoqian
Jiao, Jianbin
Zhang, Junge
Machine Learning
Artificial Intelligence
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.
title Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.00031