Author:Earle, AC; Saxe, AM; Rosman, Benjamin SDate:Aug 2017Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, learning an appropriate hierarchical decomposition of a domain into subtasks remains a substantial challenge. ...Read more
Author:Saxe, AM; Earle, AC; Rosman, Benjamin SDate:Aug 2017Hierarchical architectures are critical to the scalability of reinforcement learning methods. Most current hierarchical frameworks execute actions serially, with macro-actions comprising sequences of primitive actions. We propose a novel ...Read more