Planning in Multi-agent Environment Using Strips Representation and Non-cooperative Equilibrium Strategy

Most current studies on multi-agent evolution based on deep learning take a cooperative equilibrium strategy, while interactive self-learning is not always considered. An interactive self-learning game and evolution method based on non-cooperative equilibrium (ISGE-NCE) is proposed to take the benefits of both game theory and interactive learning for multi-agent confrontation evolution. A generative adversarial network (GAN) is designed combining with multi-agent interactive self-learning, and the non-cooperative equilibrium strategy is well adopted within the framework of interactive self-learning, aiming for high evolution efficiency and interest. For assessment, three typical multi-agent confrontation experiments are designed and conducted. The results show that, first, in terms of training speed, the ISGE-NCE produces a training convergence rate of at least 46.3% higher than that of the method without considering interactive self-learning. Second, the evolution rate of the interference and detection agents reaches 60% and 80%, respectively, after training by using our method. In the three different experiment scenarios, compared with the DDPG, our ISGE-NCE method improves the multi-agent evolution effectiveness by 43.4%, 50%, and 20%, respectively, with low training costs. The performances demonstrate the significant superiority of our ISGE-NCE method in swarm intelligence.

Download Full-text

System dynamics mechanism of cross-regional collaborative dispatch of emergency supplies based on multi-agent game

Complex & Intelligent Systems ◽

10.1007/s40747-021-00303-2 ◽

2021 ◽

Author(s):

Ying Qiu ◽

Meng Shi ◽

Xinna Zhao ◽

Yongping Jing

Keyword(s):

Evolutionary Game ◽

Specific Area ◽

Equilibrium Strategy ◽

Emergency Rescue ◽

Emergency Logistics ◽

Complexity Problem ◽

Logistics Enterprises ◽

The Face ◽

Multi Agent ◽

Multiple Variables

AbstractThe cross-regional coordinated dispatch of emergency supplies is a complex issue involving multiple topics, which covers multiple relationships and is affected by multiple variables. In the face of severe emergencies, relief supplies inside a specific area are far from meeting the explosive demand for emergency supplies. Besides, the supply of emergency materials and the disaster areas often have a spatial mismatch. Considering the attributes of externalities and public goods of emergency rescue, there are many obstacles for Local administration of emergency (LAE) and emergency logistics enterprises (ELE) spontaneously carrying out emergency supplies across regions. To solve this complexity problem, this research abstracts higher-level administration of emergency (HAE), LAE and ELE as the main stakeholders, with which a tripartite evolutionary game (ETG) model and a system dynamic (SD) model are constructed to analyze the dynamic mechanism of the complex system and to carry out the numerical simulation of the three-party game process. All the analyses and tests in this study have proved that the strong supervision of HAE has a decisive impact on the realization of cross-regional coordinated dispatch of emergency supplies, and the financial rewards and punishments imposed by HAE on other entities can accelerate or delay the achievement of the equilibrium strategy. However, when HAE chooses not to regulate, the cooperation willingness of LAE affects a lot that all the stakeholders will eventually reach equilibrium at (1,1,1) only if LAE chooses to actively carry out cross-regional coordinated dispatch of emergency supplies.

Download Full-text

A Multi-Agent Motion Prediction and Tracking Method Based on Non-Cooperative Equilibrium

Mathematics ◽

10.3390/math10010164 ◽

2022 ◽

Vol 10 (1) ◽

pp. 164

Author(s):

Yan Li ◽

Mengyu Zhao ◽

Huazhi Zhang ◽

Yuanyuan Qu ◽

Suyu Wang

Keyword(s):

Motion Prediction ◽

Random Mutation ◽

Prediction Ability ◽

Tracking Method ◽

Cooperative Equilibrium ◽

Predictive Learning ◽

Difference Function ◽

Tracking Ability ◽

Multi Agent ◽

Agent Intelligence

A Multi-Agent Motion Prediction and Tracking method based on non-cooperative equilibrium (MPT-NCE) is proposed according to the fact that some multi-agent intelligent evolution methods, like the MADDPG, lack adaptability facing unfamiliar environments, and are unable to achieve multi-agent motion prediction and tracking, although they own advantages in multi-agent intelligence. Featured by a performance discrimination module using the time difference function together with a random mutation module applying predictive learning, the MPT-NCE is capable of improving the prediction and tracking ability of the agents in the intelligent game confrontation. Two groups of multi-agent prediction and tracking experiments are conducted and the results show that compared with the MADDPG method, in the aspect of prediction ability, the MPT-NCE achieves a prediction rate at more than 90%, which is 23.52% higher and increases the whole evolution efficiency by 16.89%; in the aspect of tracking ability, the MPT-NCE promotes the convergent speed by 11.76% while facilitating the target tracking by 25.85%. The proposed MPT-NCE method shows impressive environmental adaptability and prediction and tracking ability.

Download Full-text

Research on multi-agent collaborative hunting algorithm based on game theory and Q-learning for a single escaper

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-191222 ◽

2021 ◽

Vol 40 (1) ◽

pp. 205-219

Author(s):

Yanbin Zheng ◽

Wenxin Fan ◽

Mengyun Han

Keyword(s):

Game Theory ◽

Simulation Experiment ◽

Learning Ability ◽

Equilibrium Strategy ◽

Q Learning ◽

Cooperative Hunting ◽

Multi Agent ◽

Coordination And Collaboration ◽

Agent Coordination ◽

Better Than

The multi-agent collaborative hunting problem is a typical problem in multi-agent coordination and collaboration research. Aiming at the multi-agent hunting problem with learning ability, a collaborative hunt method based on game theory and Q-learning is proposed. Firstly, a cooperative hunting team is established and a game model of cooperative hunting is built. Secondly, through the learning of the escaper’s strategy choice, the trajectory of the escaper’s limited T-step cumulative reward is established, and the trajectory is adjusted to the hunter’s strategy set. Finally, the Nash equilibrium solution is obtained by solving the cooperative hunt game, and each hunter executes the equilibrium strategy to complete the hunt task. C# simulation experiment shows that under the same conditions, this method can effectively solve the hunting problem of a single runaway with learning ability in the obstacle environment, and the comparative analysis of experimental data shows that the efficiency of this method is better than other methods.

Download Full-text