The first layer is for learning global cooperation strategy, and the second layer is for learning efficient action policy in one's own view.

第一层强化学习单元负责学习智能体的联合任务协作策略，第二层强化学习单元负责学习在本智能体看来是最有效的行动策略。

youdao

This action would not be in accord with our policy.

这一行动不会符合我们的方针。

《牛津词典》

This might mean implementing policy such as a plastic tax that adds a cost to environmentally problematic action, or banning single-use plastics altogether.

这或许是指要实施像塑料税这种会增加破坏环境行为的成本的政策，或者要全面禁用一次性塑料。

youdao

He says the class action failed because it did not target a single action or policy by Wal-Mart.

VOA: special.2011.06.24

Policy Officer at the ILO's Special Action Program to Combat Forced Labor Beate Andrees says migrant workers see themselves as risk-takers.

VOA: standard.2009.08.21

Its pledges to unwind a decades-old race-based affirmative action policy designed to give a leg up to the majority ethnic-Malay population and reduce corruption have a strong appeal among mostly younger voters, analysts say.

WSJ: Malaysia's Prime Minister Najib Razak Dissolves Parliament, Paving Way for Elections

In the current term, the court is deciding a case involving an affirmative-action policy at the University of Texas, and the court may reverse at least part of a 2003 ruling that allowed some consideration of race in university admissions.

WSJ: Voting Act Under Scrutiny

Just for starters, two years ago, the affirmative action case out of the University of Michigan, you know, she was the person who wrote the opinion that said that the affirmative action policy at the University of Michigan Law School, not the undergraduate school, was constitutional.

CNN: Toobin: O'Connor 'critical vote' on high court