We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
作者您好, 最近阅读了您对于multi-agent transformer 的文章解读,感觉受益匪浅。只是对于mat这个模型有一事不明,还望不吝赐教。根据模型描述看,该模型虽然是多智能体模型,但是顺序地通过transfomer产生每个智能体的决策。这就不免让人疑惑于,这类集中执行(centralized execution)的方法相对于单智能体的强化学习算法是否在时间复杂度上具有优势?这个问题困扰了我很久,还希望得到作者您对此的看法。
The text was updated successfully, but these errors were encountered:
将多智能体算法拆解为多个单智能体算法执行的时候一般不考虑决策顺序,可以并行执行, 通过序列决策的多智能体模型需要考虑决策顺序,通过 RNN 或者 transformer 顺序的预测下一个智能体的动作, 速度上不占优势
Sorry, something went wrong.
作者您好, 感谢您的解答。不过如果相较于单智能体的强化学习模型,mat在执行速度上不再具有多智能体决策的优势,那么mat这一算法模型似乎显得有些乏善可陈了。不知以您之见,mat作为一个顺序决策的多智能体强化学习算法,相较于单智能体强化学习算法是否有什么优势?
No branches or pull requests
作者您好,
最近阅读了您对于multi-agent transformer 的文章解读,感觉受益匪浅。只是对于mat这个模型有一事不明,还望不吝赐教。根据模型描述看,该模型虽然是多智能体模型,但是顺序地通过transfomer产生每个智能体的决策。这就不免让人疑惑于,这类集中执行(centralized execution)的方法相对于单智能体的强化学习算法是否在时间复杂度上具有优势?这个问题困扰了我很久,还希望得到作者您对此的看法。
The text was updated successfully, but these errors were encountered: