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 2102.07937cs.LGstat.ML
收藏

连续状态空间中具有形式保证的逆强化学习

Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees

Purdue University(普渡大学)

Gregory Dexter, Kevin Bello, Jean Honorio

摘要:

逆强化学习(IRL)是寻找描述观察到的/已知的专家行为的奖励函数的问题。IRL设置对于自动化控制非常有用,在奖励函数难以手动指定或作为提取代理偏好的方法的情况下。在这项工作中,我们提供了一个新的IRL算法的连续状态空间设置未知的过渡动态建模系统使用的基础上的正交函数。此外,我们提供了一个正确的证明和形式化的保证,我们的算法的样本和时间复杂度。最后,我们提出了合成实验,以证实我们的理论保证。

英文摘要:

Inverse Reinforcement Learning (IRL) is the problem of finding a reward function which describes observed/known expert behavior. The IRL setting is remarkably useful for automated control, in situations where the reward function is difficult to specify manually or as a means to extract agent preference. In this work, we provide a new IRL algorithm for the continuous state space setting with unknown transition dynamics by modeling the system using a basis of orthonormal functions. Moreover, we provide a proof of correctness and formal guarantees on the sample and time complexity of our algorithm. Finally, we present synthetic experiments to corroborate our theoretical guarantees.

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。

↑