arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.11313cs.RO
收藏

多目标操作任务的图结构策略学习

Graph-Structured Policy Learning for Multi-Goal Manipulation Tasks

Khoury College of Computer Sciences, Northeastern University(东北大学胡里计算机学院)

David Klee, Ondrej Biza, Robert Platt

摘要:

机器人操作的多目标策略学习具有挑战性。先前的成功使用了对象的基于状态的表示或提供了演示数据以促进学习。在本文中,通过手工编码域的高级离散表示,我们证明了可以使用像素Q学习的单个网络来学习达到数十个目标的策略。代理专注于学习更简单的本地策略,这些策略通过在抽象空间中进行规划而排序在一起。我们将我们的方法与标准的多目标RL基线以及其他利用离散表示的方法在具有挑战性的块构造域上进行比较。我们发现,我们的方法可以建立超过一百个不同的块结构,并证明向前转移到结构与新的对象。最后,我们将在仿真中学习的策略部署在真实机器人上。

英文摘要:

Multi-goal policy learning for robotic manipulation is challenging. Prior successes have used state-based representations of the objects or provided demonstration data to facilitate learning. In this paper, by hand-coding a high-level discrete representation of the domain, we show that policies to reach dozens of goals can be learned with a single network using Q-learning from pixels. The agent focuses learning on simpler, local policies which are sequenced together by planning in the abstract space. We compare our method against standard multi-goal RL baselines, as well as other methods that leverage the discrete representation, on a challenging block construction domain. We find that our method can build more than a hundred different block structures, and demonstrate forward transfer to structures with novel objects. Lastly, we deploy the policy learned in simulation on a real robot.

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。

↑