On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective

The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems. Consequently, IDM should possess the ability to continuously acquire new skills and effectively genera...

Full description

Saved in:
Bibliographic Details
Main Authors: Ying Wen, Ziyu Wan, Ming Zhou, Shufang Hou, Zhe Cao, Chenyang Le, Jingxiao Chen, Zheng Tian, Weinan Zhang, Jun Wang
Format: Article
Language:English
Published: Tsinghua University Press 2023-12-01
Series:CAAI Artificial Intelligence Research
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/AIR.2023.9150026
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850161082016989184
author Ying Wen
Ziyu Wan
Ming Zhou
Shufang Hou
Zhe Cao
Chenyang Le
Jingxiao Chen
Zheng Tian
Weinan Zhang
Jun Wang
author_facet Ying Wen
Ziyu Wan
Ming Zhou
Shufang Hou
Zhe Cao
Chenyang Le
Jingxiao Chen
Zheng Tian
Weinan Zhang
Jun Wang
author_sort Ying Wen
collection DOAJ
description The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems. Consequently, IDM should possess the ability to continuously acquire new skills and effectively generalize across a broad range of applications. The advancement of Artificial General Intelligence (AGI) that transcends task and application boundaries is critical for enhancing IDM. Recent studies have extensively investigated the Transformer neural architecture as a foundational model for various tasks, including computer vision, natural language processing, and reinforcement learning. We propose that a Foundation Decision Model (FDM) can be developed by formulating diverse decision-making tasks as sequence decoding tasks using the Transformer architecture, offering a promising solution for expanding IDM applications in complex real-world situations. In this paper, we discuss the efficiency and generalization improvements offered by a foundation decision model for IDM and explore its potential applications in multi-agent game AI, production scheduling, and robotics tasks. Lastly, we present a case study demonstrating our FDM implementation, DigitalBrain (DB1) with 1.3 billion parameters, achieving human-level performance in 870 tasks, such as text generation, image captioning, video game playing, robotic control, and traveling salesman problems. As a foundation decision model, DB1 represents an initial step toward more autonomous and efficient real-world IDM applications.
format Article
id doaj-art-d02f672bec0a4ad19659c9de252e31cb
institution OA Journals
issn 2097-194X
language English
publishDate 2023-12-01
publisher Tsinghua University Press
record_format Article
series CAAI Artificial Intelligence Research
spelling doaj-art-d02f672bec0a4ad19659c9de252e31cb2025-08-20T02:22:58ZengTsinghua University PressCAAI Artificial Intelligence Research2097-194X2023-12-012915002610.26599/AIR.2023.9150026On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model PerspectiveYing Wen0Ziyu Wan1Ming Zhou2Shufang Hou3Zhe Cao4Chenyang Le5Jingxiao Chen6Zheng Tian7Weinan Zhang8Jun Wang9SEIEE, Shanghai Jiao Tong University, Shanghai 200240, ChinaSEIEE, Shanghai Jiao Tong University, Shanghai 200240, ChinaSEIEE, Shanghai Jiao Tong University, Shanghai 200240, ChinaDigital Brain Laboratory, Shanghai 201306, ChinaSEIEE, Shanghai Jiao Tong University, Shanghai 200240, ChinaSEIEE, Shanghai Jiao Tong University, Shanghai 200240, ChinaSEIEE, Shanghai Jiao Tong University, Shanghai 200240, ChinaSchool of Creativity and Art, ShanghaiTech University, Shanghai 201210, ChinaSEIEE, Shanghai Jiao Tong University, Shanghai 200240, ChinaDigital Brain Laboratory, Shanghai 201306, ChinaThe pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems. Consequently, IDM should possess the ability to continuously acquire new skills and effectively generalize across a broad range of applications. The advancement of Artificial General Intelligence (AGI) that transcends task and application boundaries is critical for enhancing IDM. Recent studies have extensively investigated the Transformer neural architecture as a foundational model for various tasks, including computer vision, natural language processing, and reinforcement learning. We propose that a Foundation Decision Model (FDM) can be developed by formulating diverse decision-making tasks as sequence decoding tasks using the Transformer architecture, offering a promising solution for expanding IDM applications in complex real-world situations. In this paper, we discuss the efficiency and generalization improvements offered by a foundation decision model for IDM and explore its potential applications in multi-agent game AI, production scheduling, and robotics tasks. Lastly, we present a case study demonstrating our FDM implementation, DigitalBrain (DB1) with 1.3 billion parameters, achieving human-level performance in 870 tasks, such as text generation, image captioning, video game playing, robotic control, and traveling salesman problems. As a foundation decision model, DB1 represents an initial step toward more autonomous and efficient real-world IDM applications.https://www.sciopen.com/article/10.26599/AIR.2023.9150026artificial intelligenceintelligent decision makingtransformerfoundation decision model
spellingShingle Ying Wen
Ziyu Wan
Ming Zhou
Shufang Hou
Zhe Cao
Chenyang Le
Jingxiao Chen
Zheng Tian
Weinan Zhang
Jun Wang
On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective
CAAI Artificial Intelligence Research
artificial intelligence
intelligent decision making
transformer
foundation decision model
title On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective
title_full On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective
title_fullStr On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective
title_full_unstemmed On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective
title_short On Realization of Intelligent Decision Making in the Real World: A Foundation Decision Model Perspective
title_sort on realization of intelligent decision making in the real world a foundation decision model perspective
topic artificial intelligence
intelligent decision making
transformer
foundation decision model
url https://www.sciopen.com/article/10.26599/AIR.2023.9150026
work_keys_str_mv AT yingwen onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective
AT ziyuwan onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective
AT mingzhou onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective
AT shufanghou onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective
AT zhecao onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective
AT chenyangle onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective
AT jingxiaochen onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective
AT zhengtian onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective
AT weinanzhang onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective
AT junwang onrealizationofintelligentdecisionmakingintherealworldafoundationdecisionmodelperspective