Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

模型鲁棒性 #4

Open
wakk8 opened this issue May 27, 2024 · 2 comments
Open

模型鲁棒性 #4

wakk8 opened this issue May 27, 2024 · 2 comments

Comments

@wakk8
Copy link

wakk8 commented May 27, 2024

作者您好,想请问一下这个工作中,当我需要调整无人机的数量时,是不是需要重新训练模型,还是说训练好的模型可以运用于任意无人机数量的场景?谢谢!

@superboySB
Copy link
Contributor

superboySB commented May 27, 2024

你好,感谢关注,目前这样子的环境设计,如果修改无人机数量,需要重新训练模型。不过,也可以通过修改环境设计,进而影响网络,从而不这样子中心控制多个无人机。例如,你可以尝试像腾讯开悟比赛、网易篮球比赛那样,对英雄添加onehot标志,使用同一个网络来估计树节点价值,处理成单智能体问题后应该会在数量上有一定泛化性,但这种泛化性应该有限(如果训练场景和测试场景差了一个数量级的无人机数量,就很难了)。

@wakk8
Copy link
Author

wakk8 commented May 27, 2024

好的,谢谢作者!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants