Sequential Decision Making
时间: 2023-11-12 18:17:15 浏览: 36
Sequential Decision Making(顺序决策)是一种按时间顺序进行一系列决策的动态决策方式。它适用于随机性或不确定性动态系统的优化问题。顺序决策的目标是在每个时间步骤中选择一个最佳的动作,以使得整个序列的累积奖励最大化。这种决策过程可以用马尔可夫决策过程(Markov Decision Processes, MDP)进行建模。部分可观测马尔可夫决策过程(Partially Observable Markov Decision Processes, POMDP)是马尔可夫决策过程的一种泛化形式,适用于状态不完全可观测的情况。顺序决策还可以用来解决涉及模型不确定性、状态不确定性和多个相互作用代理的合作决策问题。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* [序贯决策的理解](https://blog.csdn.net/qq_31239371/article/details/115096523)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_2"}}] [.reference_item style="max-width: 33.333333333333336%"]
- *2* [强化学习笔记2:序列决策(Sequential Decision Making)过程](https://blog.csdn.net/qq_40206371/article/details/119223500)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_2"}}] [.reference_item style="max-width: 33.333333333333336%"]
- *3* [Decision Making Under Uncertainty](https://download.csdn.net/download/demorngel/9674146)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_2"}}] [.reference_item style="max-width: 33.333333333333336%"]
[ .reference_list ]