Event-driven muti-agent evacuation based on reinforcement learning DOI
Yuhui Liu, Ge Song, Weijian Ni

и другие.

Third International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI 2022), Год журнала: 2023, Номер unknown

Опубликована: Янв. 13, 2023

Various emergencies occur frequently, posing threats and challenges to people’s lives social security. In consequence, the evacuation of multi-Agent has become a significant part emergency response process. However, few existing works only focus on small number agents, which does not consider problem cooperation caused by increase agents impact emergencies. Therefore, framework for event-driven is proposed in this paper, includes three parts: event collection, sending, task execution. During execution, are divided into groups select leader group, while other group move with leader. Then, reinforcement learning algorithm Space Multi-Agent Deep Deterministic Policy Gradient (SMADDPG), used path planning. addition, state, action reward based Markov game designed, an environment presented as scenario. The experiment results show that method can shorten length path, improve interoperability between when occur, provide decision-making reference departments formulate plans.

Язык: Английский

An Entropy-Based Path Planning Method for Crowd Evacuation in Complex Environments DOI
Shiyu Dong, Ping Huang, Fan Wu

и другие.

Опубликована: Июнь 18, 2024

Язык: Английский

Процитировано

0

A Deep Reinforcement Learning Method for Flexible Job-Shop Scheduling Problem DOI
Changshun Shao, Zhenglin Yu,

Hongchang Ding

и другие.

Опубликована: Май 31, 2024

Язык: Английский

Процитировано

0

A Multi-Agent Motion Prediction and Tracking Method Based on Non-Cooperative Equilibrium DOI Creative Commons
Yan Li,

Mengyu Zhao,

Huazhi Zhang

и другие.

Mathematics, Год журнала: 2022, Номер 10(1), С. 164 - 164

Опубликована: Янв. 5, 2022

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 MADDPG, lack adaptability facing unfamiliar environments, are unable achieve motion prediction tracking, although they own advantages in intelligence. Featured by a performance discrimination module using time difference function together with random mutation applying predictive learning, MPT-NCE capable of improving tracking ability agents game confrontation. Two groups experiments conducted results show compared MADDPG method, aspect ability, achieves rate at more than 90%, which 23.52% higher increases whole efficiency 16.89%; promotes convergent speed 11.76% while facilitating target 25.85%. The shows impressive environmental ability.

Язык: Английский

Процитировано

1

Event-driven muti-agent evacuation based on reinforcement learning DOI
Yuhui Liu, Ge Song, Weijian Ni

и другие.

Third International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI 2022), Год журнала: 2023, Номер unknown

Опубликована: Янв. 13, 2023

Various emergencies occur frequently, posing threats and challenges to people’s lives social security. In consequence, the evacuation of multi-Agent has become a significant part emergency response process. However, few existing works only focus on small number agents, which does not consider problem cooperation caused by increase agents impact emergencies. Therefore, framework for event-driven is proposed in this paper, includes three parts: event collection, sending, task execution. During execution, are divided into groups select leader group, while other group move with leader. Then, reinforcement learning algorithm Space Multi-Agent Deep Deterministic Policy Gradient (SMADDPG), used path planning. addition, state, action reward based Markov game designed, an environment presented as scenario. The experiment results show that method can shorten length path, improve interoperability between when occur, provide decision-making reference departments formulate plans.

Язык: Английский

Процитировано

0