Information Technology Reference
In-Depth Information
Ta b l e 1 :
Utility weights for the five de- signed
personas.
Ta b l e 2 :
Agreement ratios for per-
sonas, clones, and baseline agents.
Agent
Metric Mean SD
Affordance
E
R
S
MK
TC
Personas
AAR
0.75 0.08
Move
-0.01 -0.02 -0.01 -0.01 -0.01
Clones
AAR
0.77 0.08
Monster
1
Baseline Agents
AAR
0.81 0.09
Treasure
1
Personas
TAR
0.62 0.11
Death
-1
Clones
TAR
0.66 0.13
Exit
0.5
0.5
0.5
0.5
0.5
Baseline Agents
TAR
0.61 0.13
Table 3.
Best persona matches based on Action Agreement Ratio (AAR) and Tactical
Agreement Ratio (TAR), respectively.
AAR
TAR
1 2 3 4 5 6 7 8 9 10 Total 1 2 3 4 5 6 7 8 9 10 Total
E
0 2 5 1 0 1 5 1 2 3
20 0 1 2 0 0 1 0 0 1 1
6
R
0 0 0 0 0 0 0 0 0 0
0 0 2 3 1 0 3 6 0 1 0
16
S
0 1 0 0 0 0 0 0 0 0
1 0 1 4 0 0 0 0 0 0 1
6
MK
8 8 0 2 3 1 7 2 2 0
33 5 3 1 4 0 1 2 3 4 0
23
TC
30 27 33 35 35 36 26 35 34 35
326 33 31 28 33 38 33 30 35 32 36
329
Total 38 38 38 38 38 38 38 38 38 38
380 38 38 38 38 38 38 38 38 38 38
380
6
Discussion
It seems that the AAR metric achieves higher agreement ratios than the TAR
metric. The two metrics aren't directly comparable, however, as the level's spe-
cific layout has a higher influence on the AAR value than the TAR value. Ad-
ditionally, clones and baseline agents were evolved toward AAR, rather than TAR,
for these experiments. Evolving toward TAR might have yielded different results.
Other external playtrace comparison metrics could advantageously be used for
calibration such as aggregated statistics of in-game event occurrences or other
action/edit-distance based methods such as the Gamalyzer metric [10]. The fact
that personas and clones perform roughly equally well, when mea- sured by AAR,
suggests that the persona method is a viable approach to mod- eling player
decision making styles from expert knowledge. The method is less playtrace-
dependent and computationally expensive than the cloning method, but needs an
expert game designer. Still, some players may exhibit decision making styles that
cannot be captured by the designer's intuition, and would be captured better by
the cloning approach, as suggested by the higher agreement ratios obtained from
the clones. In order to address this issue, we would propose using observed
deviation from initial persona behavior to guide the evolution of new utility
configurations for subsequently derived personas, combining the persona and
cloning approaches.
