ML-Agents中(<number of agents>, <action size>)错误

ML-Agents中使用Python API时出现The behavior needs a discrete input of dimension (xx, xx) for (<number of agents>, <action size>) but received input of dimension (xx, xx)错误

错误出现于env.set_actions()传递action至环境时出现,具体错误以下: The behavior needs a discrete input of dimension (xx, xx) for (<number of agents>, <action size>) but received input of dimension (xx, xx)

对应方法

只是discrete/continuous动作的shape没有对上,和(<number of agents>, <action size>)毫无关系,只需检查discrete/continuous动作shape即可。

Licensed under CC BY-NC-SA 4.0
comments powered by Disqus