Gameplay Analysis through State Projection

# Gameplay Analysis through State Projection

## Gameplay Analysis through State Projection

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
##### Presentation Transcript

1. Gameplay Analysis through State Projection 1 Center for Game Science Department of Computer Science University of Washington Erik Andersen1, Yun-En Liu1, Ethan Apter1, François Boucher-Genesse2, Zoran Popović1 2Department of Education • Université du Québec à Montréal FDG 2010 June 21st, 2010

2. We want to know how people play

3. We want to know how people play

4. We want to find…

5. We want to find… • Player confusion

6. We want to find… • Player confusion • Player strategies

7. We want to find… • Player confusion • Player strategies • Design flaws

8. Patterns in data SELECT * FROM replays WHERE location=x AND time>y AND attempt>3 AND death=“grenade”…

9. Patterns in data SELECT * FROM replays WHERE location=x AND time>y AND attempt>3 AND death=“grenade”… Confusion? Strategies?

11. Statistical Methods • Surveys • In-game statistics

12. Statistical Methods • Surveys • In-game statistics

13. Visual Data Mining Lets people see patterns in data Bungie (Halo 3)

14. Visual Data Mining Lets people see patterns in data • Dynamic information? Bungie (Halo 3)

15. Visual Data Mining Lets people see patterns in data • Dynamic information? • Games with no map? Bungie (Halo 3)

16. But what about?

17. But what about?

18. But what about?

19. But what about?

20. “Playtraces” Start Goal

21. “Playtraces” Start Goal

22. “Playtraces” Start Goal

23. “Playtraces” Start Goal Confusion? Distance to goal

24. Refraction

25. Refraction • Massive educational data mining

26. Classic Multidimensional Scaling • 2-D projection of points in high-dimensional space • Clusters game states based on some distance function

27. State Distance

28. State Distance

29. State Distance

30. State Distance

31. Action Distance • da (s1, s2)

32. State Distance Start Goal Confusion? Distance to goal

33. Distance to Goal • dg (s1, s2) = abs(dg (s1, sg) - dg (s2, sg))

34. Distance Functions Action distance Distance to goal Combined

35. Refraction Distance Function • d (s1, s2) = (da (s1, s2) + dg (s1, s2)) / 2

36. Playtracer Framework

37. Easy level

38. Difficult level

39. Failure

40. Chance To Win

41. Chance To Win

42. Evaluation