马尔可夫决策过程
Markov Decision Processes
Martin L. Puterman · 初版 1994 年
2人推荐
3位读者提及
3次提及
过去十年见证了关于 Markov decision processes 的大量理论与应用研究，以及这些模型在生态学、经济学、通信工程和其他结果不确定且需要序贯决策过程的领域中日益广泛的应用。为了及时回应这一日益活跃的趋势，Martin L. Puterman 的新作对 Markov decision process 模型的理论、计算和应用研究进行了独具特色的前沿、统一且严谨的阐述。本书讨论了该领域的所有主要研究方向，突出了许多重要的
Hacker News 上怎么说
正在加载完整评论……
多臂老虎机（multi-armed bandits）理论源于对马尔可夫决策过程（MDP）的研究。这一领域在随机控制和动态规划中也有深入研究且紧密相关。关于 MDP 的一本好书是 Martin… 写的《Markov Decision Processes: Discrete Stochastic Dynamic Programming》
The theory of multi-armed bandits arises from the study of Markov decision processes (MDP). This field is also closely studied in and related to Stochastic Control and Dynamic Programming. A good book on MDP's is "Markov Decision Processes: Discrete Stochastic Dynamic Programming by Martin…
我强烈推荐 Sergey Levine 的课程：http://rail.eecs.berkeley.edu/deeprlcourse/ 如果想看更偏数学的处理方式，Puterman 写过一本极好的书：https://www.amazon.com/Markov-Decision-Processes-Stochastic-...
I would highly recommend Sergey Levine's course: http://rail.eecs.berkeley.edu/deeprlcourse/ For a more mathematical treatment, there's a beautiful book by Puterman: https://www.amazon.com/Markov-Decision-Processes-Stochastic-...
你真该去多读读关于马尔可夫决策过程（MDP）以及博弈论（Game Theory）的内容。在这个语境下，“求解”（solve）是有严格定义的，楼主用得完全准确。所谓“求解”一个博弈，就是找到能让期望收益最大化的 policy。显然……
You should read more about Markov Decision Processes (MDPs) and Game Theory in general. The word "solve" is well defined in this context, and is used accurately by OP. You "solve" a game by finding the policy that maximizes the expected return. Obviously…