arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.10075cs.LGcs.AIcs.RO
收藏

通过多步策略回归方法学习规划

Learning to Plan via a Multi-Step Policy Regression Method

Heinrich Heine University Düsseldorf(杜塞尔多夫海因里希·海涅大学)

Stefan Wagner, Michael Janschek, Tobias Uelwer, Stefan Harmeling

摘要:

我们提出了一种新的方法,以提高推理性能的环境中,需要一个特定的动作序列,以解决。这是例如迷宫环境的情况,其中理想地确定最优路径。我们不是学习单步的的策略,而是学习一个可以提前预测n个动作的策略。我们提出的方法称为政策地平线回归(PHR)使用A2C采样的环境知识,学习一个n维的政策向量的政策蒸馏设置,产生n个连续的行动,每个观察。我们在MiniGrid和Pong环境中测试了我们的方法,并通过成功预测单个观察的动作序列,在推理时间内显示出大幅加速。

英文摘要:

We propose a new approach to increase inference performance in environments that require a specific sequence of actions in order to be solved. This is for example the case for maze environments where ideally an optimal path is determined. Instead of learning a policy for a single step, we want to learn a policy that can predict n actions in advance. Our proposed method called policy horizon regression (PHR) uses knowledge of the environment sampled by A2C to learn an n dimensional policy vector in a policy distillation setup which yields n sequential actions per observation. We test our method on the MiniGrid and Pong environments and show drastic speedup during inference time by successfully predicting sequences of actions on a single observation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑