A multi-agent based real-time strategy game playing method

A multi-agent and game technology, applied in the field of multi-agent games, reinforcement learning, and human-machine confrontation, can solve problems such as search decision degradation and shallow search depth, and achieve better decision-making effects

Active Publication Date: 2021-08-31
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But when the number of agents increases, the search depth will become shallower, and the obtained search decision will be degenerate

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A multi-agent based real-time strategy game playing method
  • A multi-agent based real-time strategy game playing method
  • A multi-agent based real-time strategy game playing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with aspects of the invention as recited in the appended claims.

[0073] The UCT search algorithm is suitable for continuous real-time strategy games, and can give action feedback to multiple agents in a continuous space. However, the UCT search algorithm has a fixed exploration ratio in search decisions and cannot adapt to changes in real-time scenes.

[0074] In some embodiments, in the small-scale game scene, in the multi-agent-based real-time strategy game...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention provides a multi-agent based real-time strategic game playing method, including: AERUCT search algorithm: adaptively adjust the exploration ratio according to the current blood volume and winning rate, perform forward search, and calculate the evaluation of the search direction according to the current state value, select the next search direction according to the evaluation value of the search direction; the AERUCT search algorithm is an improved UCT search algorithm; the performance of the AERUCT search algorithm will be improved in small-scale game scenarios, but due to large-scale game scenarios The number of nodes for search decision-making increases and is limited by time. The UCTRL algorithm stores and updates the strategy with good performance and compares it with the results of the AERUCT search, evaluates and selects child nodes with a high winning rate, and updates the status information in reverse. Repeat this process to ensure that the current strategy is not worse than The previous strategy makes each agent smarter and improves learning ability.

Description

technical field [0001] This application relates to the fields of reinforcement learning, man-machine confrontation, and multi-agent games, and in particular to a multi-agent-based real-time strategic game playing method. Background technique [0002] Real-time strategy (RTS) games are not turn-based games, but video games. Players manage resources, build different types of structures, and direct how they play against opponents. Current research mainly focuses on micromanipulation, game strategy and optimal path. Game strategy is especially important when the number of agents and the attack capabilities of both sides are the same. Therefore, researchers have done a lot of research on multi-agent game strategies. [0003] Script-based and search-tree algorithms are often used in real-time strategy games, and classic script-based strategy algorithms use a strategy in one round, such as attacking the closest enemy or attacking the weakest enemy first, etc. The PGS algorithm ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): A63F13/822G06N20/00
CPCA63F13/822G06N20/00
Inventor 张俊格尹奇跃于彤彤
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap