arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.09999cs.LGcs.ROcs.SYeess.SY
收藏

逆约束强化学习

Inverse Constrained Reinforcement Learning

Information Technology University(信息技术大学);Georgia State University(佐治亚州立大学)

Usman Anwar, Shehryar Malik, Alireza Aghasi, Ali Ahmed

摘要:

在现实世界的设置中,存在许多难以数学地指定的约束。然而,对于强化学习(RL)的现实世界部署,RL代理意识到这些约束是至关重要的,以便他们可以安全地采取行动。在这项工作中,我们考虑的问题,学习约束,从演示的约束遵守代理的行为。我们的实验验证了我们的方法,并表明我们的框架可以成功地学习代理尊重的最有可能的约束。我们进一步表明,这些学习的约束是\textit{transferable}的新代理,可能有不同的形态和/或奖励功能。以前的工作在这方面主要是限制到表格(离散)设置,特定类型的约束或假设环境的过渡动态。相比之下,我们的框架是能够学习任意的\textit{Markovian}的约束,在一个完全无模型的设置在高维度。代码可以找到它:\url{https://github.com/shehryar-malik/icrl} .

英文摘要:

In real world settings, numerous constraints are present which are hard to specify mathematically. However, for the real world deployment of reinforcement learning (RL), it is critical that RL agents are aware of these constraints, so that they can act safely. In this work, we consider the problem of learning constraints from demonstrations of a constraint-abiding agent's behavior. We experimentally validate our approach and show that our framework can successfully learn the most likely constraints that the agent respects. We further show that these learned constraints are \textit{transferable} to new agents that may have different morphologies and/or reward functions. Previous works in this regard have either mainly been restricted to tabular (discrete) settings, specific types of constraints or assume the environment's transition dynamics. In contrast, our framework is able to learn arbitrary \textit{Markovian} constraints in high-dimensions in a completely model-free setting. The code can be found it: \url{https://github.com/shehryar-malik/icrl}.

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。

↑