Skip to content
#

asynchronous-training

Here is 1 public repository matching this topic...

本项目是一个基于 MuZero 和 Gumbel 搜索构建的三人八子棋(Eight-in-a-Row)AI 训练与对弈系统。该系统采用了 DeepSeek MLA 作为网络骨干,并深度集成了课程学习(Curriculum Learning)、联赛机制(League)、基于种群的训练(PBT)、Engram 情节记忆以及 EfficientZero 的一致性损失等高级强化学习技术。此外,项目支持同步与多进程异步训练,并提供了基于 FastAPI 的实时对弈服务以及基于 WebSocket 的可视化训练监控台。

  • Updated Feb 25, 2026
  • Python

Improve this page

Add a description, image, and links to the asynchronous-training topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the asynchronous-training topic, visit your repo's landing page and select "manage topics."

Learn more