Deep Reinforcement Learning Agent for Negotiation in Multi-Agent Cooperative Distributed Predictive Control
This paper proposes a novel solution for using deep neural networks with reinforcement learning as a valid option in negotiating distributed hierarchical controller agents. The proposed method is implemented in the upper layer of a hierarchical control architecture composed at its lowest levels by d...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/4/2432 |
| _version_ | 1797622530422341632 |
|---|---|
| author | Oscar Aponte-Rengifo Pastora Vega Mario Francisco |
| author_facet | Oscar Aponte-Rengifo Pastora Vega Mario Francisco |
| author_sort | Oscar Aponte-Rengifo |
| collection | DOAJ |
| description | This paper proposes a novel solution for using deep neural networks with reinforcement learning as a valid option in negotiating distributed hierarchical controller agents. The proposed method is implemented in the upper layer of a hierarchical control architecture composed at its lowest levels by distributed control based on local models and negotiation processes with fuzzy logic. The advantage of the proposal is that it does not require the use of models in the negotiation, and it facilitates the minimization of any dynamic behavior index and the specification of constraints. Specifically, it uses a reinforcement learning policy gradient algorithm to achieve a consensus among the agents. The algorithm is successfully applied to a level system composed of eight interconnected tanks that are quite difficult to control due to their non-linear nature and the high interaction among their subsystems. |
| first_indexed | 2024-03-11T09:11:37Z |
| format | Article |
| id | doaj.art-04e0fea933b0412084ec3be8e450fb2f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:11:37Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-04e0fea933b0412084ec3be8e450fb2f2023-11-16T18:55:40ZengMDPI AGApplied Sciences2076-34172023-02-01134243210.3390/app13042432Deep Reinforcement Learning Agent for Negotiation in Multi-Agent Cooperative Distributed Predictive ControlOscar Aponte-Rengifo0Pastora Vega1Mario Francisco2Department of Computer Science and Automatics, Faculty of Sciences, University of Salamanca, Plaza de la Merced, s/n, 37008 Salamanca, SpainDepartment of Computer Science and Automatics, Faculty of Sciences, University of Salamanca, Plaza de la Merced, s/n, 37008 Salamanca, SpainDepartment of Computer Science and Automatics, Faculty of Sciences, University of Salamanca, Plaza de la Merced, s/n, 37008 Salamanca, SpainThis paper proposes a novel solution for using deep neural networks with reinforcement learning as a valid option in negotiating distributed hierarchical controller agents. The proposed method is implemented in the upper layer of a hierarchical control architecture composed at its lowest levels by distributed control based on local models and negotiation processes with fuzzy logic. The advantage of the proposal is that it does not require the use of models in the negotiation, and it facilitates the minimization of any dynamic behavior index and the specification of constraints. Specifically, it uses a reinforcement learning policy gradient algorithm to achieve a consensus among the agents. The algorithm is successfully applied to a level system composed of eight interconnected tanks that are quite difficult to control due to their non-linear nature and the high interaction among their subsystems.https://www.mdpi.com/2076-3417/13/4/2432deep reinforcement learningdistributed model predictive controlmulti-agentfuzzy logic |
| spellingShingle | Oscar Aponte-Rengifo Pastora Vega Mario Francisco Deep Reinforcement Learning Agent for Negotiation in Multi-Agent Cooperative Distributed Predictive Control Applied Sciences deep reinforcement learning distributed model predictive control multi-agent fuzzy logic |
| title | Deep Reinforcement Learning Agent for Negotiation in Multi-Agent Cooperative Distributed Predictive Control |
| title_full | Deep Reinforcement Learning Agent for Negotiation in Multi-Agent Cooperative Distributed Predictive Control |
| title_fullStr | Deep Reinforcement Learning Agent for Negotiation in Multi-Agent Cooperative Distributed Predictive Control |
| title_full_unstemmed | Deep Reinforcement Learning Agent for Negotiation in Multi-Agent Cooperative Distributed Predictive Control |
| title_short | Deep Reinforcement Learning Agent for Negotiation in Multi-Agent Cooperative Distributed Predictive Control |
| title_sort | deep reinforcement learning agent for negotiation in multi agent cooperative distributed predictive control |
| topic | deep reinforcement learning distributed model predictive control multi-agent fuzzy logic |
| url | https://www.mdpi.com/2076-3417/13/4/2432 |
| work_keys_str_mv | AT oscaraponterengifo deepreinforcementlearningagentfornegotiationinmultiagentcooperativedistributedpredictivecontrol AT pastoravega deepreinforcementlearningagentfornegotiationinmultiagentcooperativedistributedpredictivecontrol AT mariofrancisco deepreinforcementlearningagentfornegotiationinmultiagentcooperativedistributedpredictivecontrol |