8,811 Hits in 5.9 sec

Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions [article]

Michael Chang, Sidhant Kaushik, S. Matthew Weinberg, Thomas L. Griffiths, Sergey Levine
2020 arXiv   pre-print
We derive a class of decentralized reinforcement learning algorithms that are broadly applicable not only to standard reinforcement learning but also for selecting options in semi-MDPs and dynamically  ...  What makes it challenging to use a decentralized approach to collectively optimize a central objective is the difficulty in characterizing the equilibrium strategy profile of non-cooperative games.  ...  Semi-MDPs and Computation Graphs One benefit of framing global decision-making from the perspective of local economic transactions is that the same societal decision-making framework and learning algorithms  ... 
arXiv:2007.02382v2 fatcat:yyzxjhe5gfcavdrbjw6vvb62eu

Decentralizing Air Traffic Flow Management with Blockchain-based Reinforcement Learning

Ta Duong, Ketan Kumar Todi, Umang Chaudhary, Hong-Linh Truong
2019 2019 IEEE 17th International Conference on Industrial Informatics (INDIN)  
Index Terms-decentralized optimization, air traffic flow management, blockchain, reinforcement learning, multi-agent systems  ...  Our system, named BlockAgent, leverages the inherent synergy between multi-agent reinforcement learning (RL) for air traffic flow optimization; and the rising blockchain technology for a secure, transparent  ...  systems for intelligent decision making, to offer a natural solution for the regional ATFM problem.  ... 
doi:10.1109/indin41052.2019.8972225 dblp:conf/indin/DuongTCT19 fatcat:2edeienchrfyvc6zhdmvasstd4

Decentralized Collective Learning for Self-managed Sharing Economies

Evangelos Pournaras, Peter Pilgerstorfer, Thomas Asikis
2018 ACM Transactions on Autonomous and Adaptive Systems  
This paper contributes new experimental indings about the inluence of network topology and planning on learning eiciency as well as indings on techno-socio-economic trade-ofs and global optimality.  ...  When agents self-determine options from which they choose, for instance their resource consumption and production, while these choices have a collective system-wide impact, optimal decision-making turns  ...  Such complex techno-socio-economic systems are large in size, online and involve decision-making processes with combinatorial complexity, i.e. optimization of collective decisions is required to prevent  ... 
doi:10.1145/3277668 fatcat:e7gxxn2rebcnhc3rq4mtya2qz4

Blockchain-based Federated Learning: A Comprehensive Survey [article]

Zhilin Wang, Qin Hu
2021 arXiv   pre-print
Federated learning (FL) can prevent privacy leakage by assigning training tasks to multiple clients, thus separating the central server from the local devices.  ...  However, issues of privacy and scalability will constrain the development of machine learning.  ...  The model in [64] considers the above issues and designs a deep reinforcement learning methodology to help the machine learning model owner to make the optimal decisions to reduce transmission delay  ... 
arXiv:2110.02182v1 fatcat:sm2mtftvq5fodgkfdhcan55n3q

Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey [article]

Tianxu Li, Kun Zhu, Nguyen Cong Luong, Dusit Niyato, Qihui Wu, Yang Zhang, Bing Chen
2022 arXiv   pre-print
Each entity may need to make its local decision to improve the network performance under dynamic and uncertain network environments.  ...  decision-making policy adaptively through interacting with the unknown environments.  ...  decision-making solutions to the network entity through global optimization, e.g., through the centralized training with decentralized execution (CTDE) framework.  ... 
arXiv:2110.13484v2 fatcat:u2o5uxms65gmnp3q7xbh35l5oi

Deep Reinforcement Learning Algorithms in Intelligent Infrastructure

2019 Infrastructures  
Neurons of artificial neural networks are associated with a prediction or decision layer based on a deep reinforcement learning algorithm that takes into consideration all of its previous learning.  ...  In addition, the proposed method makes decisions based on real time data.  ...  Deep Reinforcement Learning Deep learning enables reinforcement learning to scale decision making solutions that were previously unmanageable.  ... 
doi:10.3390/infrastructures4030052 fatcat:xipi3sx5fva2lkt3iqpvwyff5e

Blockchain-Enabled Federated Learning for UAV Edge Computing Network: Issues and Solutions

Chaoyang Zhu, Xiao Zhu, Junyu Ren, Tuanfa Qin
2022 IEEE Access  
Compared to traditional machine learning, federated learning requires a decentralized distribution system to enhance trust for UAVs.  ...  More recently, the concept of federal learning (FL) has been set up to protect mobile user data privacy.  ...  However, in our UBFL architecture, global model calculations are performed directly on the UAVs in a decentralized manner via blockchain [84] .  ... 
doi:10.1109/access.2022.3174865 fatcat:gkleclw5b5fwneylx2mhxerjnm

Effective Management for Blockchain-Based Agri-Food Supply Chains Using Deep Reinforcement Learning

Huilin Chen, Zheyi Chen, Feiting Lin, Peifen Zhuang
2021 IEEE Access  
Next, a Deep Reinforcement learning based Supply Chain Management (DR-SCM) method is proposed to make effective decisions on the production and storage of agri-food products for profit optimization.  ...  INDEX TERMS Agri-food supply chains, agri-food safety, product traceability, profit optimization, blockchain, deep reinforcement learning. 36008 This work is licensed under a Creative Commons Attribution  ...  Therefore, the proposed framework can ensure a decentralized security for the agri-food tracing data in ASCs. • A Deep Reinforcement learning based Supply Chain Management (DR-SCM) method is proposed to  ... 
doi:10.1109/access.2021.3062410 fatcat:qgz6l7r6cnb4zppatxwkduhcxa

Reinforcement Learning in Blockchain-Enabled IIoT Networks: A Survey of Recent Advances and Open Challenges

Furqan Jameel, Uzair Javaid, Wali Ullah Khan, Muhammad Naveed Aman, Haris Pervaiz, Riku Jäntti
2020 Sustainability  
It is a decentralized, secure, and auditable solution for exchanging, and authenticating information via transactions, without the need of a trusted third party.  ...  Based on these observations, the article then promotes the utility of reinforcement learning (RL) techniques to address some of the major issues of blockchain-enabled IIoT networks such as block time minimization  ...  Characteristics and Overview of Reinforcement Learning Techniques Reinforcement learning (RL) is a sub-branch of AI or, more generally, of computer science that deals with having computers solve problems  ... 
doi:10.3390/su12125161 fatcat:4jabrpmxbnhz3pnym76rixi7ye

Externalities, Learning and Governance: New Perspectives on Local Economic Development

Bert Helmsing
2001 Development and Change  
This article reviews three partially overlapping perspectives on local economic development, which derive from three factors intensifying the localized nature of economic development: externalities, learning  ...  The dynamics of local economic development are increasingly associated with evolutionary economic thinking in general and with collective learning in particular.  ...  Globalization of trade and the growing mobility of production make restructuring a more frequent problem of new local economic development.  ... 
doi:10.1111/1467-7660.00206 fatcat:lul7mlky2bafbbrarpthol2v2u

Blockchain-Based Federated Learning in UAVs Beyond 5G Networks: A Solution Taxonomy and Future Directions

Deepti Saraswat, Ashwin Verma, Pronaya Bhattacharya, Sudeep Tanwar, Gulshan Sharma, Pitshou N. Bokoro, Ravi Sharma
2022 IEEE Access  
Federated learning (FL) allows data to be trained on local nodes, preserving privacy and improving network communication.  ...  INDEX TERMS Beyond 5G networks, 6G, blockchain, federated learning, unmanned aerial vehicles. D. ORGANIZATION AND READING MAP  ...  (ANN), genetic algorithm, and reinforcement learning-ant colony optimization (RL-ACO) for efficient decision making, and results are offloaded back to users upon fulfillment of the task's execution.  ... 
doi:10.1109/access.2022.3161132 fatcat:4h6ormfvjfd45n25vvzkynvyg4

A Trusted Routing Scheme Using Blockchain and Reinforcement Learning for Wireless Sensor Networks

Jidian Yang, Shiwen He, Yang Xu, Linweiya Chen, Ju Ren
2019 Sensors  
The reinforcement learning model is used to help routing nodes dynamically select more trusted and efficient routing links.  ...  In view of these problems, this paper proposes a trusted routing scheme using blockchain and reinforcement learning to improve the routing security and efficiency for WSNs.  ...  R i then selects the next-hop routing node R π via the routing policy π obtained by the local learning model.  ... 
doi:10.3390/s19040970 fatcat:z44t436p5bh5tipb3wx5w6mz5a

Blockchain-Empowered Mobile Edge Intelligence, Machine Learning and Secure Data Sharing [chapter]

Yao Du, Shuxiao Miao, Zitian Tong, Victoria Lemieux, Zehua Wang
2021 Blockchain Potential in AI [Working Title]  
With the advent of new decentralized machine learning approaches and mobile edge computing, the IoT on-device data training has now become possible.  ...  As a distributed smart ledger, blockchain is renowned for high scalability, privacy-preserving, and decentralization.  ...  [64] present a reinforcement learning-based offloading scheme that assists mobile miners to determine optimal offloading decisions, reduce energy consumption, and avoid network latency.  ... 
doi:10.5772/intechopen.96618 fatcat:tjon4elghrcq5e5lfsfmyx2srm

Integrated multi-scale data analytics and machine learning for the distribution grid

Emma M. Stewart, Philip Top, Michael Chertkov, Deepjyoti Deka, Scott Backhaus, Andrey Lokhov, Ciaran Roberts, Val Hendrix, Sean Peisert, Anthony Florita, Thomas J. King, Matthew J. Reno
2017 2017 IEEE International Conference on Smart Grid Communications (SmartGridComm)  
multi-variate analytics machine-learning-based applications.  ...  This paper describes benefits and limits of present machinelearning applications for use on the grid and presents a series of case studies that illustrate the potential benefits of developing advanced local  ...  Transactive control applications are generally designed to be self-organizing and localized; that is, they are decentralized and not coordinated.  ... 
doi:10.1109/smartgridcomm.2017.8340693 dblp:conf/smartgridcomm/StewartTCDBLRHP17 fatcat:zmu4jrdptbfnrn2yne4kclksw4

Learning 4.0 - Ambition Guide [article]

Marcos António Nogueira, Elsa Nunes, Rui Pedro Henriques, Elena Vishniakova, Paula Peiró
2022 Zenodo  
Constant improvements of sources and platforms will lead, firstly, to the development of tools and services to manage transactions for local markets, as well as decentralized supply and demand management  ...  Blockchain is used in the leading economic sector, where it is used for payments and cybersecurity, as well as accelerate transactions, increase transparency and verifiability of transactions, and almost  ... 
doi:10.5281/zenodo.5817159 fatcat:k35u3kyhyrfw3feyxfwlnduiwq
« Previous Showing results 1 — 15 out of 8,811 results