A New Efficient Method for Refining the Reinforcement Learning Algorithm to Train Deep Q Agents for Reaching a Consensus in P2P Networks
The usage of distributed Peer-to-Peer (P2P) networks has been growing steadily for a reasonable period. Various applications rely on the infrastructure of P2P networks, where nodes communicate to accomplish a task without the need for a central authority. One of the significant challenges in P2P net...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10105270/ |
| _version_ | 1797840085672001536 |
|---|---|
| author | Arafat Abu Mallouh Zakariya Qawaqneh Omar Abuzaghleh Ahmad Al-Rababa'A |
| author_facet | Arafat Abu Mallouh Zakariya Qawaqneh Omar Abuzaghleh Ahmad Al-Rababa'A |
| author_sort | Arafat Abu Mallouh |
| collection | DOAJ |
| description | The usage of distributed Peer-to-Peer (P2P) networks has been growing steadily for a reasonable period. Various applications rely on the infrastructure of P2P networks, where nodes communicate to accomplish a task without the need for a central authority. One of the significant challenges in P2P networks is the ability of the network nodes to reach a consensus on a shared item; the challenge increases as time passes. Thus, this work proposes a new effective method for tweaking the Deep Reinforcement Learning (DRL) algorithm to train Deep Q Network (DQN) learning agents to reach a consensus among the P2P nodes. We propose various hierarchies of deep agents to address this crucial challenge in P2P networks. DRL is utilized to build and train agents; more precisely, DQN learning agents are constructed and trained. Two scenarios are proposed and evaluated. In the first scenario, one DQN agent is trained to find the consensus between the network nodes. In the second scenario, three hierarchies with different numbers of layers of agents are proposed and evaluated. In both scenarios, the P2P network used is a blockchain network. The best result was obtained using the third hierarchy of the second scenario; the overall accuracy of the model is 87.8%. |
| first_indexed | 2024-04-09T16:08:46Z |
| format | Article |
| id | doaj.art-876490b019314715a090da5ec5bec6d0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T16:08:46Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-876490b019314715a090da5ec5bec6d02023-04-24T23:00:43ZengIEEEIEEE Access2169-35362023-01-0111386653867910.1109/ACCESS.2023.326828310105270A New Efficient Method for Refining the Reinforcement Learning Algorithm to Train Deep Q Agents for Reaching a Consensus in P2P NetworksArafat Abu Mallouh0https://orcid.org/0000-0002-5953-1506Zakariya Qawaqneh1Omar Abuzaghleh2Ahmad Al-Rababa'A3https://orcid.org/0000-0003-3995-8956Computer Science Department, Manhattan College, Riverdale, NY, USADepartment of Computing Sciences, State University of New York Brockport, Brockport, NY, USADepartment of Computer Information Science, Higher Colleges of Technology, Dubai, United Arab EmiratesComputer Science Department, The World Islamic Science and Education University, Amman, JordanThe usage of distributed Peer-to-Peer (P2P) networks has been growing steadily for a reasonable period. Various applications rely on the infrastructure of P2P networks, where nodes communicate to accomplish a task without the need for a central authority. One of the significant challenges in P2P networks is the ability of the network nodes to reach a consensus on a shared item; the challenge increases as time passes. Thus, this work proposes a new effective method for tweaking the Deep Reinforcement Learning (DRL) algorithm to train Deep Q Network (DQN) learning agents to reach a consensus among the P2P nodes. We propose various hierarchies of deep agents to address this crucial challenge in P2P networks. DRL is utilized to build and train agents; more precisely, DQN learning agents are constructed and trained. Two scenarios are proposed and evaluated. In the first scenario, one DQN agent is trained to find the consensus between the network nodes. In the second scenario, three hierarchies with different numbers of layers of agents are proposed and evaluated. In both scenarios, the P2P network used is a blockchain network. The best result was obtained using the third hierarchy of the second scenario; the overall accuracy of the model is 87.8%.https://ieeexplore.ieee.org/document/10105270/Blockchainconsensusdeep reinforcement learningDQNP2P |
| spellingShingle | Arafat Abu Mallouh Zakariya Qawaqneh Omar Abuzaghleh Ahmad Al-Rababa'A A New Efficient Method for Refining the Reinforcement Learning Algorithm to Train Deep Q Agents for Reaching a Consensus in P2P Networks IEEE Access Blockchain consensus deep reinforcement learning DQN P2P |
| title | A New Efficient Method for Refining the Reinforcement Learning Algorithm to Train Deep Q Agents for Reaching a Consensus in P2P Networks |
| title_full | A New Efficient Method for Refining the Reinforcement Learning Algorithm to Train Deep Q Agents for Reaching a Consensus in P2P Networks |
| title_fullStr | A New Efficient Method for Refining the Reinforcement Learning Algorithm to Train Deep Q Agents for Reaching a Consensus in P2P Networks |
| title_full_unstemmed | A New Efficient Method for Refining the Reinforcement Learning Algorithm to Train Deep Q Agents for Reaching a Consensus in P2P Networks |
| title_short | A New Efficient Method for Refining the Reinforcement Learning Algorithm to Train Deep Q Agents for Reaching a Consensus in P2P Networks |
| title_sort | new efficient method for refining the reinforcement learning algorithm to train deep q agents for reaching a consensus in p2p networks |
| topic | Blockchain consensus deep reinforcement learning DQN P2P |
| url | https://ieeexplore.ieee.org/document/10105270/ |
| work_keys_str_mv | AT arafatabumallouh anewefficientmethodforrefiningthereinforcementlearningalgorithmtotraindeepqagentsforreachingaconsensusinp2pnetworks AT zakariyaqawaqneh anewefficientmethodforrefiningthereinforcementlearningalgorithmtotraindeepqagentsforreachingaconsensusinp2pnetworks AT omarabuzaghleh anewefficientmethodforrefiningthereinforcementlearningalgorithmtotraindeepqagentsforreachingaconsensusinp2pnetworks AT ahmadalrababaa anewefficientmethodforrefiningthereinforcementlearningalgorithmtotraindeepqagentsforreachingaconsensusinp2pnetworks AT arafatabumallouh newefficientmethodforrefiningthereinforcementlearningalgorithmtotraindeepqagentsforreachingaconsensusinp2pnetworks AT zakariyaqawaqneh newefficientmethodforrefiningthereinforcementlearningalgorithmtotraindeepqagentsforreachingaconsensusinp2pnetworks AT omarabuzaghleh newefficientmethodforrefiningthereinforcementlearningalgorithmtotraindeepqagentsforreachingaconsensusinp2pnetworks AT ahmadalrababaa newefficientmethodforrefiningthereinforcementlearningalgorithmtotraindeepqagentsforreachingaconsensusinp2pnetworks |