大规模无折扣马尔可夫决策过程的新近似动态规划算法及其在生产与分销系统优化中的应用

New approximate dynamic programming algorithms for large-scale undiscounted Markov decision processes and their application to optimize a production and distribution system

• Katsuhisa Ohno
• Toshitaka Boh
• Koichi Nakade
• Takayoshi Tamura 通讯