一种智能体博弈训练方法、系统、设备及存储介质
By estimating the asymmetric and incomplete information state of the opponent agent in agent games and updating the dynamic win function online, the cognitive bias problem of agents in uncertain environments is solved, and the decision-making and game-playing capabilities of agents are improved.
CN117669773BActive Publication Date: 2026-07-17UNIV OF SCI & TECH OF CHINA
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV OF SCI & TECH OF CHINA
- Filing Date
- 2023-12-11
- Publication Date
- 2026-07-17
Smart Images
Figure CN117669773B_ABST
Abstract
本发明公开了一种智能体博弈训练方法、系统、设备及存储介质，克服了在非对称且非完全信息条件下，智能体对未知对手行为等高属性特征认知偏差带来的赢得值偏差的传递和放大。本发明以在线更新表征智能体所采策略的相对优势评分的动态赢得函数以及表征对手策略的状态估计网络的方式，解决多智能体博弈的中策略迁移导致的环境非平稳性，动态适应智能体的状态迁移，能够提升智能体的性能。
Need to check novelty before this filing date? Find Prior Art