مشخصات پژوهش

عنوان	A Local Graph Clustering Algorithm for Discovering Subgoals in Reinforcement Learning
نوع پژوهش	مقاله ارائه شده کنفرانسی
کلیدواژه‌ها	Hierarchical Reinforcement Learning, Option, Skill Acquisition,Subgoal Discovery, Graph Clustering.
چکیده	Reinforcement Learning studies the problem of learning through in-teraction with the unknown environment. Learning efficiently in large scale problems and complex tasks demands a decomposition of the original complex task to simple and smaller subtasks. In this paper a local graph clustering algo-rithm is represented for discovering subgoals. The main advantage of the pro-posed algorithm is that only the local information of the graph is considered to cluster the agent state space. Subgoals discovered by the algorithm are then used to generate skills. Experimental results show that the proposed subgoal discovery algorithm has a dramatic effect on the learning performance.
پژوهشگران	پرهام مرادی دولت آبادی (نفر سوم)، محمد ابراهیم شیری (نفر دوم)، نگین انتظاری (نفر اول)