论文标题
具有少量目标功能的计划
Planning with Submodular Objective Functions
论文作者
论文摘要
我们以下目标功能进行研究计划，而不是最大化累积奖励，而是最大程度地提高了下函数引起的客观值。我们的框架包含标准计划和suppodular最大化，并以特殊情况为特殊情况，因此在我们的框架中可以自然提出许多实际应用。基于多线性扩展的概念，我们提出了一个新颖的，理论上原则性的算法框架，用于使用suppodular目标函数进行计划，当应用于上述两个特殊案例时，它将恢复经典算法。从经验上讲，我们的方法在合成环境和导航任务上大大优于基线算法。
We study planning with submodular objective functions, where instead of maximizing the cumulative reward, the goal is to maximize the objective value induced by a submodular function. Our framework subsumes standard planning and submodular maximization with cardinality constraints as special cases, and thus many practical applications can be naturally formulated within our framework. Based on the notion of multilinear extension, we propose a novel and theoretically principled algorithmic framework for planning with submodular objective functions, which recovers classical algorithms when applied to the two special cases mentioned above. Empirically, our approach significantly outperforms baseline algorithms on synthetic environments and navigation tasks.
