Personalized Adaptive Training Improves Performance at a Professional First-Person Shooter Action Videogame

Abstract

First-Person Shooter (FPS) game experience can be transferred to untrained cognitive functions such as attention, visual short-term memory, spatial cognition, and decision-making. However, previous studies have been using off-the-shelf FPS games based on predefined gaming settings, therefore it is not known whether such improvement of in game performance and transfer of abilities can be further improved by creating a in-game, adaptive in-game training protocol. To address this question, we compared the impact of a popular FPS-game (Counter-Strike:Global-Offensive-CS:GO) with an ad hoc version of the game based on a personalized, adaptive algorithm modifying the artificial intelligence of opponents as well as the overall game difficulty on the basis of individual gaming performance. Two groups of FPS-naïve healthy young participants were randomly assigned to playing one of the two game versions (11 and 10 participants, respectively) 2 h/day for 3 weeks in a controlled laboratory setting, including daily in-game performance monitoring and extensive cognitive evaluations administered before, immediately after, and 3 months after training. Participants exposed to the adaptive version of the game were found to progress significantly faster in terms of in-game performance, reaching gaming scenarios up to 2.5 times more difficult than the group exposed to standard CS:GO (p < 0.05). A significant increase in cognitive performance was also observed. Personalized FPS gaming can significantly speed-up the learning curve of action videogame-players, with possible future applications for expert-video-gamers and potential relevance for clinical-rehabilitative applications.

Keywords: cognitive training; first-person shooter; human learning; videogame; videogame training.

FIGURE 1

Scheme of the experiment protocol. (A) At the beginning of the game, the player could join one of the two teams available in the game: Team 1 or Team 2. The A-CS:GO group played a customized game in which the progression in the game was established on the bases of the Death/Kill (K/D) ratio. If a player reached the K/D ≥ 2/1 for two consecutive rounds, he/she could proceed into the next level. Once reaching level 24, participants restarted from level 17 and could proceed to the next level only if he/she was capable of reaching a K/D ≥ 3/1. The D-CS:GO players could choose their difficulty level between four standardized games at the beginning of each round (*players joined a team and faced some enemies. The number of team bots and enemy bots was customized, as well as their skills^∗). (B) Weapons’ efficacy was set from the less (green–yellow) to the most (yellow–orange) dangerous on the bases of the extent of the capacity to cause damage, firing rate, and reload velocity. (C) Four different maps were available in the game. The smallest and easiest maps (Shorttrain and Shortdust) characterized the first levels of the A-CS:GO group and the Easy/Normal modality in the D-CS:GO group, whereas larger maps (Bank and Office) were proposed to challenge subjects in the A-CS:GO group and in Hard/Expert modality of the D-CS:GO group.

FIGURE 2

Game skills assessment. (A) During the initial assessment, each player completed 40′ of tutorial to understand the game controls and the environment. (B) At T0 and T1, subjects completed the Aim Course time-constrained task. The times required to complete the Aim Course 1 and Aim Course 2 Maps were registered. (C) At T0 and T1, the participants engaged in various shooting tasks and accuracy was recorded. (D) At the initial assessment, the A-CS:GO group was further assessed on a fourth task, aiming to define the level of player game-ability. This task established the player’s starting level.

FIGURE 3

Graphical depiction of the in-game progression for both A-CS:GO and D-CS:GO groups. (A) uncorrected K/D ratio, difficulty levels and corrected K/D ratio of the training rounds. (B) Individual corrected K/D ratio changes during training rounds. (C) K/D ratio during the training days. (D) Corrected K/D ratio during the training days. After an initial equivalent performance between A-CS:GO and D-CS:GO groups, the corrected K/D ratio progressively increased in the A-CS:GO group and the performance of the A-CS:GO group becomes significantly higher than the CS:GO group performance. (*p < 0.05 – higher performance in the A-CS:GO group). E: Pre-training corrected K/D was subtracted from post-training performance for both groups, highlighting a significant improvement of performance after the A-CS:GO training (*p < 0.05).

FIGURE 4

Long Term Cognitive Transfer results. Graphical depictions of the significant effects observed between cognitive assessments (^∗significant difference between T1 and T0; ^∗∗significant difference between T2 and T0; Global/Local Task: ∇: Global Features ○: Local Features).