Open Access
June 2014 MONEYBaRL: Exploiting pitcher decision-making using Reinforcement Learning
Gagan Sidhu, Brian Caffo
Ann. Appl. Stat. 8(2): 926-955 (June 2014). DOI: 10.1214/13-AOAS712


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.

The necessary Markovian probabilities can be estimated by the relevant observed conditional proportions in MLB pitch-by-pitch game data. These probabilities could be pitcher-specific, using only the data from one pitcher, or general, using the data from a collection of pitchers.

Optimal batting strategies against these estimated conditional distributions of pitch selection can be ascertained by Value Iteration. Optimal batting strategies against a pitcher-specific conditional distribution can be contrasted to those calculated from the general conditional distributions associated with a collection of pitchers.

In this manuscript, a single season of MLB data is used to calculate the conditional distributions to find optimal pitcher-specific and general (against a collection of pitchers) batting strategies. These strategies are subsequently evaluated by conditional distributions calculated from a different season for the same pitchers. Thus, the batting strategies are conceptually tested via a collection of simulated games, a “mock season,” governed by distributions not used to create the strategies. (Simulation is not needed, as exact calculations are available.)

Instances where the pitcher-specific batting strategy outperforms the general batting strategy suggests that the pitcher is exploitable—knowledge of the conditional distributions of their pitch-making decision process in a different season yielded a strategy that worked better in a new season than a general batting strategy built on a population of pitchers. A permutation-based test of exploitability of the collection of pitchers is given and evaluated under two sets of assumptions.

To show the practical utility of the approach, we introduce a spatial component that classifies each pitcher’s pitch-types using a batter-parameterized spatial trajectory for each pitch. We found that heuristically labeled “nonelite” batters benefit from using the exploited pitchers’ pitcher-specific strategies, whereas (also heuristically labeled) “elite” players do not.


Download Citation

Gagan Sidhu. Brian Caffo. "MONEYBaRL: Exploiting pitcher decision-making using Reinforcement Learning." Ann. Appl. Stat. 8 (2) 926 - 955, June 2014.


Published: June 2014
First available in Project Euclid: 1 July 2014

zbMATH: 06333782
MathSciNet: MR3262540
Digital Object Identifier: 10.1214/13-AOAS712

Keywords: algorithmic statistics , baseball , Markov , simulation , sports

Rights: Copyright © 2014 Institute of Mathematical Statistics

Vol.8 • No. 2 • June 2014
Back to Top