arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1407.8392cs.AIstat.AP
收藏

MONEYBaRL:利用强化学习开发投手决策

MONEYBaRL: Exploiting pitcher decision-making using Reinforcement Learning

General Analytics;University of Alberta(阿尔伯塔大学);Johns Hopkins University(约翰斯·霍普金斯大学)

Gagan Sidhu, Brian Caffo

摘要:

这篇手稿使用机器学习技术来利用棒球投手的决策,所谓的“棒球智商”,通过建模的击球信息,球场选择和计数,作为一个马尔可夫决策过程(MDP)。MDP的每个状态都以马尔可夫的方式模拟投手的当前投球选择,条件是在做出当前投球之前的信息。这包括在前一个投球之前的计数,他随后的投球选择,击球手随后的动作和投球的结果。

英文摘要:

This manuscript uses machine learning techniques to exploit baseball pitchers' decision making, so-called "Baseball IQ," by modeling the at-bat information, pitch selection and counts, as a Markov Decision Process (MDP). Each state of the MDP models the pitcher's current pitch selection in a Markovian fashion, conditional on the information immediately prior to making the current pitch. This includes the count prior to the previous pitch, his ensuing pitch selection, the batter's ensuing action and the result of the pitch.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑