Many-objective stochastic path finding using reinforcement learning

详细信息    查看全文

• 作者：Bentz Tozer ; ^{bentz@gwu.edu} ; Thomas Mazzuchi ^{mazzu@gwu.edu} ; Shahram Sarkani ^{sarkani@gwu.edu}
• 关键词：Many objective reinforcement learning ; Stochastic path finding ; Sequential decision making under uncertainty ; Social choice theory
• 刊名：Expert Systems with Applications
• 出版年：2017
• 出版时间：15 April 2017
• 年：2017
• 卷：72
• 期：Complete
• 页码：371-382
• 全文大小：1950 K
• 卷排序：72

文摘

A novel many-objective reinforcement learning algorithm is proposed. A benchmark many-objective pathfinding problem is introduced. We evaluated the algorithm on path finding problems with five and six objectives. Total reward obtained, solution set quality, and episode duration were measured. The proposed method outperforms the state of the art on all problems.