可压缩受限度量策略最优化问题
Compactly Restrictable Metric Policy Optimization Problems
摘要：
我们研究具有度量状态和动作空间的确定性马尔可夫决策过程（MDP）的策略最优化问题，我们称之为度量策略最优化问题（MPOPs）.我们的目标是建立理论结果的适定性的MPOPs，可以表征实际相关的连续控制系统。要做到这一点，我们定义了一个特殊的类的MPOP称为Compensable限制MPOP（CR-MPOP），这是足够灵活，以捕捉机器人系统的复杂行为，但具体到足够承认解决方案，使用动态规划方法，如值迭代。我们展示了如何使用前向不变性来获得CR-MPOP。我们进一步表明，我们的理论结果CR-MPOPs可以用来描述反馈线性化控制仿射系统。
英文摘要：
We study policy optimization problems for deterministic Markov decision processes (MDPs) with metric state and action spaces, which we refer to as Metric Policy Optimization Problems (MPOPs). Our goal is to establish theoretical results on the well-posedness of MPOPs that can characterize practically relevant continuous control systems. To do so, we define a special class of MPOPs called Compactly Restrictable MPOPs (CR-MPOPs), which are flexible enough to capture the complex behavior of robotic systems but specific enough to admit solutions using dynamic programming methods such as value iteration. We show how to arrive at CR-MPOPs using forward-invariance. We further show that our theoretical results on CR-MPOPs can be used to characterize feedback linearizable control affine systems.
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。
