Rocket League Skillshots

Donated on 8/14/2023

This dataset contains data of players of the game Rocket League, performing different skillshots.

Dataset Characteristics

Tabular, Time-Series

Subject Area

Games

Associated Tasks

Classification

Feature Type

Real

# Instances

297

# Features

-

Dataset Information

Additional Information

Each skillshot performed is characterized by 18 features, composed of players inputs and in-game metrics, collected at different time, creating a multivariate time serie. You can see what skillshots look like in the github of the project: https://github.com/Romathonat/RocketLeagueSkillsDetection

Has Missing Values?

No

Introductory Paper

A Behavioral Pattern Mining Approach to Model Player Skills in Rocket League

By Romain Mathonat, Jean-François Boulicaut, Mehdi Kaytoue-Uberall. 2020

Published in 2020 IEEE Conference on Games (CoG)

Variable Information

The first line contains the name of each of the 18 features. The format is the following: class_number BallAcceleration_1, Time_1, ..., jump_1 BallAcceleration_2, Time_2, ..., jump_2 ... BallAcceleration_n, Time_n, ..., jump_n class_number

Class Labels

There are seven classes, -1 representing noise (composed of failed figures and random moves) Note that lengths of those multivariate timeseries vary and that sample is not collected at regular time interval (see paper for more details). -1: noise 1: ceiling shot 2: power shot 3: waving dash 5: air dribble 6: front flick 7: musty flick

Reviews

There are no reviews for this dataset yet.

Login to Write a Review
Download
1 citations
5449 views

Keywords

videogame

Creators

Romain Mathonat

romain.mathonat@gmail.com

University de Lyon, CNRS, INSA Lyon

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy