马尔可夫决策过程中可解释策略的修正单调策略迭代及状态排序规则的影响

Modified monotone policy iteration for interpretable policies in Markov decision processes and the impact of state ordering rules

Annals of Operations Research · 2024
被引 2
ABS 3
马尔可夫决策过程强化学习可解释人工智能优化算法