arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.03447math.OC
收藏

平均LQR问题的收敛性及其在强化学习中的应用

Convergence results for an averaged LQR problem with applications to reinforcement learning

Andrea Pesare, Michele Palladino, Maurizio Falcone

摘要:

本文研究一类动态未知的线性二次型最优控制问题。作为一个建模假设,我们将假设智能体对当前系统的知识由矩阵空间上的概率分布$π$表示。此外,我们将假设这样的概率测度被适时地更新,以考虑智能体在探索环境时获得的增加的经验,从而以增加的准确性近似潜在的动态。在这些假设下,我们将证明,通过解决"平均"线性二次型最优控制问题相对于一定的$π$的最优控制收敛到最优控制驱动相关的线性二次型最优控制问题所支配的实际,潜在的动态。这种方法与基于模型的强化学习算法密切相关,其中描述不确定性系统知识的先验和后验概率分布被递归更新。在最后一节中,我们将展示一个数值测试,证实了理论结果。

英文摘要:

In this paper, we will deal with a Linear Quadratic Optimal Control problem with unknown dynamics. As a modeling assumption, we will suppose that the knowledge that an agent has on the current system is represented by a probability distribution $π$ on the space of matrices. Furthermore, we will assume that such a probability measure is opportunely updated to take into account the increased experience that the agent obtains while exploring the environment, approximating with increasing accuracy the underlying dynamics. Under these assumptions, we will show that the optimal control obtained by solving the "average" Linear Quadratic Optimal Control problem with respect to a certain $π$ converges to the optimal control driven related to the Linear Quadratic Optimal Control problem governed by the actual, underlying dynamics. This approach is closely related to model-based Reinforcement Learning algorithms where prior and posterior probability distributions describing the knowledge on the uncertain system are recursively updated. In the last section, we will show a numerical test that confirms the theoretical results.

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。

↑