arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.16044cs.LGcs.AI
收藏

具有奖励型先验的低维状态表示学习

Low Dimensional State Representation Learning with Reward-shaped Priors

University of Twente(特文特大学);Jönköping University(延雪平大学);Saxion University of Applied Sciences(萨克逊应用科学大学)

Nicolò Botteghi, Ruben Obbink, Daan Geijs, Mannes Poel, Beril Sirmacek, Christoph Brune, Abeje Mersha, Stefano Stramigioli

摘要:

强化学习已经能够解决许多复杂的机器人任务,而不需要端到端的特征工程。然而,直接从感官输入(即观察)学习最优策略通常需要处理和存储大量数据。在机器人领域,来自真实机器人硬件的数据成本通常非常高,因此需要实现高采样效率的解决方案。我们提出了一种方法,旨在学习从观测到一个低维状态空间的映射。这种映射是通过无监督学习来学习的,该学习使用被成形为结合环境和任务的先验知识的损失函数。利用状态空间中的样本,快速有效地学习最优策略。我们测试的方法在几个移动机器人导航任务的仿真环境中,也对一个真正的机器人。

英文摘要:

Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations, often requires processing and storage of a huge amount of data. In the context of robotics, the cost of data from real robotics hardware is usually very high, thus solutions that achieve high sample-efficiency are needed. We propose a method that aims at learning a mapping from the observations into a lower-dimensional state space. This mapping is learned with unsupervised learning using loss functions shaped to incorporate prior knowledge of the environment and the task. Using the samples from the state space, the optimal policy is quickly and efficiently learned. We test the method on several mobile robot navigation tasks in a simulation environment and also 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。

↑