期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 6, 期 4, 页码 6250-6257出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2021.3092676
关键词
Learning from demonstration; probabilistic inference; formal methods in robotics and automation
类别
资金
- National Science Foundation under the CAREER Award [SHF-2048094, CCF-1837131, CNS-1932620]
- Toyota RD
Learning control policies that are safe, robust and interpretable is a major challenge in developing robotic systems. Using formal logic in learning-from-demonstrations is a new paradigm in reinforcement learning to estimate rewards and extract robot control policies to overcome these challenges. The approach involves inferring rewards automatically from user demonstrations based on specified logic, ranking them to determine optimal control policies.
Learning control policies that are safe, robust and interpretable are prominent challenges in developing robotic systems. Learning-from-demonstrations with formal logic is an arising paradigm in reinforcement learning to estimate rewards and extract robot control policies that seek to overcome these challenges. In this approach, we assume that mission-level specifications for the robotic system are expressed in a suitable temporal logic such as Signal Temporal Logic (STL). The main idea is to automatically infer rewards from user demonstrations (that could be suboptimal or incomplete) by evaluating and ranking them w.r.t. the given STL specifications. In contrast to existing work that focuses on deterministic environments and discrete state spaces, in this letter, we propose significant extensions that tackle stochastic environments and continuous state spaces.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据