Pursuit-Evasion Games for Multi-agent Based on Reinforcement Learning with Obstacles

Penglin Hu, Yaning Guo, Jinwen Hu, Quan Pan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Considering the problem of external interference and obstacle avoidance in multi-agent pursuit-evasion games, the deep deterministic policy gradient algorithm is used to train agents in continuous space. Obstacle and collision avoidance are realized by designing detailed reward function. Interference data are added to the original observations, and adversarial learning algorithm is used to eliminate the influence of interference and other agents. The evaluation function based on heading angle and relative distance is used to evalue evader’s escape strategy, which improves the robustness of the proposed algorithm. Simulation experiments are designed to verify the effectiveness of the algorithm.

Original languageEnglish
Title of host publicationProceedings of 2022 International Conference on Autonomous Unmanned Systems, ICAUS 2022
EditorsWenxing Fu, Mancang Gu, Yifeng Niu
PublisherSpringer Science and Business Media Deutschland GmbH
Pages1015-1024
Number of pages10
ISBN (Print)9789819904785
DOIs
StatePublished - 2023
EventInternational Conference on Autonomous Unmanned Systems, ICAUS 2022 - Xi'an, China
Duration: 23 Sep 202225 Sep 2022

Publication series

NameLecture Notes in Electrical Engineering
Volume1010 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Autonomous Unmanned Systems, ICAUS 2022
Country/TerritoryChina
CityXi'an
Period23/09/2225/09/22

Keywords

  • Deep deterministic policy gradient
  • Environmental disturbance
  • Obstacle avoidance
  • Pursuit-evasion games
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'Pursuit-Evasion Games for Multi-agent Based on Reinforcement Learning with Obstacles'. Together they form a unique fingerprint.

Cite this