Learning from human demonstrations for real-time case-based planning

One of the main bottlenecks in deploying case-based planning systems is authoring the case-base of plans. In this paper we will present a collec-tion of algorithms that can be used to automatically learn plans from human demonstrations. Our al-gorithms are based on the basic idea of a plan de-pendency graph, which is a graph that captures the dependencies among actions in a plan. Such algo-rithms are implemented in a system called Darmok 2 (D2), a case-based planning system capable of general game playing with a focus on real-time strategy (RTS) games. We evaluate D2 with a col-lection of three different games with promising re-sults.