Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact

Repository Web            Google
View ALL Data Sets

SkillCraft1 Master Table Dataset Data Set
Download: Data Folder, Data Set Description

Abstract: This data was used in Thompson et al. (2013). A list of possible game actions is discussed in Thompson, Blair, Chen, & Henrey (2013).

Data Set Characteristics:  


Number of Instances:




Attribute Characteristics:

Integer, Real

Number of Attributes:


Date Donated


Associated Tasks:


Missing Values?


Number of Web Hits:



-- Creators: Mark Blair, Joe Thompson, Andrew Henrey, Bill Chen
-- Mark Blair: Department of Psychology; Simon Fraser University; Burnaby;
8888 University Drive; mblair '@'
-- Date: September, 20, 2013

Data Set Information:

-- We aggregated screen movements into screen-fixations using a Salvucci & Goldberg (2000) dispersion-threshold algorithm, and defined Perception Action Cycles (PACs) as fixations with at least one action.
-- Time is recorded in terms of timestamps in the StarCraft 2 replay file. When the game is played on 'faster', 1 real-time second is equivalent to roughly 88.5 timestamps.
-- List of possible game actions is discussed in Thompson, Blair, Chen, & Henrey (2013)

Attribute Information:

1. GameID: Unique ID number for each game (integer)
2. LeagueIndex: Bronze, Silver, Gold, Platinum, Diamond, Master, GrandMaster, and Professional leagues coded 1-8 (Ordinal)
3. Age: Age of each player (integer)
4. HoursPerWeek: Reported hours spent playing per week (integer)
5. TotalHours: Reported total hours spent playing (integer)
6. APM: Action per minute (continuous)
7. SelectByHotkeys: Number of unit or building selections made using hotkeys per timestamp (continuous)
8. AssignToHotkeys: Number of units or buildings assigned to hotkeys per timestamp (continuous)
9. UniqueHotkeys: Number of unique hotkeys used per timestamp (continuous)
10. MinimapAttacks: Number of attack actions on minimap per timestamp (continuous)
11. MinimapRightClicks: number of right-clicks on minimap per timestamp (continuous)
12. NumberOfPACs: Number of PACs per timestamp (continuous)
13. GapBetweenPACs: Mean duration in milliseconds between PACs (continuous)
14. ActionLatency: Mean latency from the onset of a PACs to their first action in milliseconds (continuous)
15. ActionsInPAC: Mean number of actions within each PAC (continuous)
16. TotalMapExplored: The number of 24x24 game coordinate grids viewed by the player per timestamp (continuous)
17. WorkersMade: Number of SCVs, drones, and probes trained per timestamp (continuous)
18. UniqueUnitsMade: Unique unites made per timestamp (continuous)
19. ComplexUnitsMade: Number of ghosts, infestors, and high templars trained per timestamp (continuous)
20. ComplexAbilitiesUsed: Abilities requiring specific targeting instructions used per timestamp (continuous)

Relevant Papers:

1. Thompson JJ, Blair MR, Chen L, Henrey AJ (2013) Video Game Telemetry as a Critical Tool in the Study of Complex Skill Learning. PLoS ONE 8(9): e75129. [Web Link]
-- Results:
-- Skip league conditional inference forest classification (Bronze-Gold;Silver-Platinum;Gold-Diamond;Platinum-Masters;Diamond-Professional) showed changing patterns of variable importance with skill.
-- Predicted attribute: League (Ordinal)

Citation Request:

You are free to copy, distribute and transmit this work under the following conditions: You must give attribution to the work (but not in any way that suggests that the author endorses you or your use of the work); You may not use this work for commercial purposes; You may not alter, transform, or build upon this work. Any further uses require the permission of the rights holder (or author if no rights holder is listed). These rights are based on the Creative Commons Attribution-NonCommercial-NoDerivatives License.

Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML