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 2302.03586cs.LGcs.AI
收藏

安全关键控制的自适应聚集

Adaptive Aggregation for Safety-Critical Control

McGill University(麦吉尔大学)

Huiliang Zhang, Di Wu, Benoit Boulet

摘要:

安全性被认为是阻止将强化学习(RL)用于现实世界应用的主要障碍。已经开发了不同的方法来处理RL中的安全问题。然而,学习可靠的基于RL的解决方案通常需要与环境进行大量的交互。同样,如何提高学习效率,具体地说,如何利用迁移学习进行安全的强化学习,还没有得到很好的研究。在这项工作中,我们提出了一个自适应聚合框架的安全关键控制。我们的方法包括两个关键技术:1)我们学习通过聚合多个源任务和目标任务通过注意力网络的安全知识的传输; 2)我们分开的目标,提高任务的性能和减少约束违反通过使用一个安全措施。实验结果表明,我们的算法可以实现更少的安全违规,同时表现出更好的数据效率相比,几个基线。

英文摘要:

Safety has been recognized as the central obstacle to preventing the use of reinforcement learning (RL) for real-world applications. Different methods have been developed to deal with safety concerns in RL. However, learning reliable RL-based solutions usually require a large number of interactions with the environment. Likewise, how to improve the learning efficiency, specifically, how to utilize transfer learning for safe reinforcement learning, has not been well studied. In this work, we propose an adaptive aggregation framework for safety-critical control. Our method comprises two key techniques: 1) we learn to transfer the safety knowledge by aggregating the multiple source tasks and a target task through the attention network; 2) we separate the goal of improving task performance and reducing constraint violations by utilizing a safeguard. Experiment results demonstrate that our algorithm can achieve fewer safety violations while showing better data efficiency compared with several baselines.

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。

↑