Recurrent Macro Actions Generator for POMDP Planning
Yuanchu Liang,Hanna Kurniawati,Yuanchu Liang,Hanna Kurniawati
Many planning problems in robotics require long planning horizon and uncertain in nature. The Par-tially Observable Markov Descision Process (POMDP) is a mathematically principled framework for planning under uncertainty. To alleviate the difficulties of computing good approximate POMDP solutions for long horizon problems, one often plans using macro actions, where each macro action is a chain of ...
