On the convergence of cycle detection for navigational reinforcement learning

Autor:	Ameloot, Tom J., Bussche, Jan Van den
Rok vydání:	2015
Předmět:	Computer Science - Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	We consider a reinforcement learning framework where agents have to navigate from start states to goal states. We prove convergence of a cycle-detection learning algorithm on a class of tasks that we call reducible. Reducible tasks have an acyclic solution. We also syntactically characterize the form of the final policy. This characterization can be used to precisely detect the convergence point in a simulation. Our result demonstrates that even simple algorithms can be successful in learning a large class of nontrivial tasks. In addition, our framework is elementary in the sense that we only use basic concepts to formally prove convergence.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1511.08724 Zobrazit plný text záznamu View this record from Arxiv