马尔可夫决策过程的时间连接
Temporal Concatenation for Markov Decision Processes
摘要：
我们提出并分析了一个时间级联启发式求解大规模有限时域马尔可夫决策过程（MDP），它将MDP划分为较小的子问题沿时域和生成一个整体的解决方案，通过简单地连接这些子问题的最优解。作为一个“黑盒”架构，时间级联与广泛的现有MDP算法。我们的主要结果表征遗憾的时间串联相比，最优解。我们提供一般MDP实例的上界，以及一个家庭的MDP实例中的上界被证明是紧的。总之，我们的研究结果表明，时间级联的潜力，大量的速度在一些性能下降的代价。
英文摘要：
We propose and analyze a temporal concatenation heuristic for solving large-scale finite-horizon Markov decision processes (MDP), which divides the MDP into smaller sub-problems along the time horizon and generates an overall solution by simply concatenating the optimal solutions from these sub-problems. As a "black box" architecture, temporal concatenation works with a wide range of existing MDP algorithms. Our main results characterize the regret of temporal concatenation compared to the optimal solution. We provide upper bounds for general MDP instances, as well as a family of MDP instances in which the upper bounds are shown to be tight. Together, our results demonstrate temporal concatenation's potential of substantial speed-up at the expense of some performance degradation.
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。
