Memristive Bellman solver for decision-making

Abstract The Bellman equation, with a resource-consuming solving process, plays a fundamental role in formulating and solving dynamic optimization problems. The realization of the Bellman solver with memristive computing-in-memory (MCIM) technology, is significant for implementing efficient dynamic...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhe Feng, Zuheng Wu, Jianxun Zou, Lingli Cheng, Xiaolong Zhao, Xumeng Zhang, Jian Lu, Cong Wang, Yilin Wang, Haochen Wang, Wenbin Guo, Zhibin Qian, Yunlai Zhu, Zuyu Xu, Yuehua Dai, Qi Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-60085-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704288270417920
author Zhe Feng
Zuheng Wu
Jianxun Zou
Lingli Cheng
Xiaolong Zhao
Xumeng Zhang
Jian Lu
Cong Wang
Yilin Wang
Haochen Wang
Wenbin Guo
Zhibin Qian
Yunlai Zhu
Zuyu Xu
Yuehua Dai
Qi Liu
author_facet Zhe Feng
Zuheng Wu
Jianxun Zou
Lingli Cheng
Xiaolong Zhao
Xumeng Zhang
Jian Lu
Cong Wang
Yilin Wang
Haochen Wang
Wenbin Guo
Zhibin Qian
Yunlai Zhu
Zuyu Xu
Yuehua Dai
Qi Liu
author_sort Zhe Feng
collection DOAJ
description Abstract The Bellman equation, with a resource-consuming solving process, plays a fundamental role in formulating and solving dynamic optimization problems. The realization of the Bellman solver with memristive computing-in-memory (MCIM) technology, is significant for implementing efficient dynamic decision-making. However, the iterative nature of the Bellman equation solving process poses a challenge for efficient implementation on MCIM systems, which excel at vector-matrix multiplication (VMM) operations but are less suited for iterative algorithms. In this work, by incorporating the temporal dimension and transforming the solution into recurrent dot product operations, a memristive Bellman solver (MBS) is proposed, facilitating the implementation of the Bellman equation solving process with efficient MCIM technology. The MBS effectively reduces the iteration numbers and which further enhanced by approximated solutions leveraging memristor noise. Finally, the path planning tasks are used to verify the feasibility of the proposed MBS. The theoretical derivation and experimental results demonstrate that the MBS effectively reduces the iteration cycles, facilitating the solving efficiency. This work could be a sound of choice for developing high-efficiency decision-making systems.
format Article
id doaj-art-92e34997b5f04bd9b925d93f8a9d565b
institution DOAJ
issn 2041-1723
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-92e34997b5f04bd9b925d93f8a9d565b2025-08-20T03:16:47ZengNature PortfolioNature Communications2041-17232025-05-0116111110.1038/s41467-025-60085-wMemristive Bellman solver for decision-makingZhe Feng0Zuheng Wu1Jianxun Zou2Lingli Cheng3Xiaolong Zhao4Xumeng Zhang5Jian Lu6Cong Wang7Yilin Wang8Haochen Wang9Wenbin Guo10Zhibin Qian11Yunlai Zhu12Zuyu Xu13Yuehua Dai14Qi Liu15School of Integrated Circuits, Anhui UniversitySchool of Integrated Circuits, Anhui UniversitySchool of Integrated Circuits, Anhui UniversityFrontier Institute of Chip and System, Fudan UniversitySchool of Microelectronics, University of Science and Technology of ChinaFrontier Institute of Chip and System, Fudan UniversityResearch Center for Intelligent Computing Hardware, Zhejiang LaboratoryInstitute of Brain-inspired Intelligence, National Laboratory of Solid State Microstructures, School of Physics, Collaborative Innovation Center of Advanced Microstructures, Nanjing UniversitySchool of Microelectronics, University of Science and Technology of ChinaSchool of Integrated Circuits, Anhui UniversitySchool of Integrated Circuits, Anhui UniversitySchool of Integrated Circuits, Anhui UniversitySchool of Integrated Circuits, Anhui UniversitySchool of Integrated Circuits, Anhui UniversitySchool of Integrated Circuits, Anhui UniversityFrontier Institute of Chip and System, Fudan UniversityAbstract The Bellman equation, with a resource-consuming solving process, plays a fundamental role in formulating and solving dynamic optimization problems. The realization of the Bellman solver with memristive computing-in-memory (MCIM) technology, is significant for implementing efficient dynamic decision-making. However, the iterative nature of the Bellman equation solving process poses a challenge for efficient implementation on MCIM systems, which excel at vector-matrix multiplication (VMM) operations but are less suited for iterative algorithms. In this work, by incorporating the temporal dimension and transforming the solution into recurrent dot product operations, a memristive Bellman solver (MBS) is proposed, facilitating the implementation of the Bellman equation solving process with efficient MCIM technology. The MBS effectively reduces the iteration numbers and which further enhanced by approximated solutions leveraging memristor noise. Finally, the path planning tasks are used to verify the feasibility of the proposed MBS. The theoretical derivation and experimental results demonstrate that the MBS effectively reduces the iteration cycles, facilitating the solving efficiency. This work could be a sound of choice for developing high-efficiency decision-making systems.https://doi.org/10.1038/s41467-025-60085-w
spellingShingle Zhe Feng
Zuheng Wu
Jianxun Zou
Lingli Cheng
Xiaolong Zhao
Xumeng Zhang
Jian Lu
Cong Wang
Yilin Wang
Haochen Wang
Wenbin Guo
Zhibin Qian
Yunlai Zhu
Zuyu Xu
Yuehua Dai
Qi Liu
Memristive Bellman solver for decision-making
Nature Communications
title Memristive Bellman solver for decision-making
title_full Memristive Bellman solver for decision-making
title_fullStr Memristive Bellman solver for decision-making
title_full_unstemmed Memristive Bellman solver for decision-making
title_short Memristive Bellman solver for decision-making
title_sort memristive bellman solver for decision making
url https://doi.org/10.1038/s41467-025-60085-w
work_keys_str_mv AT zhefeng memristivebellmansolverfordecisionmaking
AT zuhengwu memristivebellmansolverfordecisionmaking
AT jianxunzou memristivebellmansolverfordecisionmaking
AT linglicheng memristivebellmansolverfordecisionmaking
AT xiaolongzhao memristivebellmansolverfordecisionmaking
AT xumengzhang memristivebellmansolverfordecisionmaking
AT jianlu memristivebellmansolverfordecisionmaking
AT congwang memristivebellmansolverfordecisionmaking
AT yilinwang memristivebellmansolverfordecisionmaking
AT haochenwang memristivebellmansolverfordecisionmaking
AT wenbinguo memristivebellmansolverfordecisionmaking
AT zhibinqian memristivebellmansolverfordecisionmaking
AT yunlaizhu memristivebellmansolverfordecisionmaking
AT zuyuxu memristivebellmansolverfordecisionmaking
AT yuehuadai memristivebellmansolverfordecisionmaking
AT qiliu memristivebellmansolverfordecisionmaking