AI 中文总结
研究重球Q值迭代的收敛与加速问题,借助切换线性系统理论和联合谱半径,将其转化为精确的切换线性系统来分析收敛性,并研究其比标准Q值迭代更快的条件。
AI 中文摘要
我们研究了带动量的Q值迭代(QVI),即重球QVI的收敛性和加速问题。虽然价值迭代的加速已被广泛研究,但针对控制任务的重球QVI加速研究较少。我们从切换线性系统(SLS)理论和联合谱半径(JSR)的角度分析重球QVI。首先将其转化为精确的SLS并通过JSR解释其收敛性,还从基于JSR的角度研究了重球QVI比标准QVI更快的条件。
英文摘要
We study the convergence and acceleration of Qvalue iteration (QVI) with heavy-ball momentum. Although acceleration of value iteration has been studied extensively, there has been less work on the acceleration of heavy-ball QVI for control tasks. We analyze heavy-ball QVI from the viewpoint of switched linear system (SLS) theory and the joint spectral radius (JSR). First, we convert heavy-ball QVI into an exact SLS and interpret its convergence through the JSR. We also give JSR-based conditions under which heavy-ball QVI can be faster than standard QVI.