for RTS Games Alberto Uriarte and Santiago Ontañón Drexel University Philadelphia November 16 2015 Motivation To use a gametree search algorithm we need a forward model or simulator ID: 467694
Download Presentation The PPT/PDF document "Automatic Learning of Combat Models" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Automatic Learning of Combat Models for RTS Games
Alberto
Uriarte and Santiago Ontañón
Drexel University
Philadelphia
November 16, 2015Slide2
MotivationTo use a game-tree search algorithm we need a forward model
or “simulator”.In some games (like StarCraft) we don’t have such forward model.
The most complex part of a forward model for RTS games is the combat.Slide3
The goalFast and high-level
combat simulator.
Why fast?
To use algorithms like MCTS we need to simulate thousands of combats really quick.
Why
high-level
?
Even an “attrition game” (an
abstraction of a combat game where units cannot move) is EXPTIME
1
. So this is already a hard problem. A
high-level model reduces branching factor.
1
Furtak
and
Buro
(2010)Slide4
Proposed combat simulators
Sustained DPF model
Compute how much time each army needs to destroy the other using the Damage Per Frame
of each group.
Remove the army that took longer to destroy enemy.Remove casualties from winner army using a
target policy
.
Input
High-level abstraction of units: number of each unit type by player.
Output
Surviving units.
Decreased DPF model
Compute how much time to kill one
enemy’s unit
.
Remove the unit killed and reduce HP of survivors.
Back to point
1 until one army is destroyed
.Slide5
Proposed combat simulators
Sustained DPF model
Compute how much time each army needs to destroy the other using the Damage Per Frame
of each group.
Remove the army that took longer to destroy enemy.Remove casualties from winner army using a
target policy
.
Input
High-level abstraction of units: number of each unit type by player.
Output
Surviving
units.
Decreased DPF model
Compute how much time to kill one
enemy’s unit
.
Remove the unit killed a reduce HP of survivors.
Back to point
1 until one army is destroyed
.
PROs
Simpler and Faster
PROs
Can be stopped at any time to have a prediction
after X fames
More accurate predictionsSlide6
Models parameters
Unit DPF
Hardcoded
Computed
using the weapon damage and the time between shots.
Learned
When
a unit is killed compute the (unit’s HP / time attacking unit) / number of attackers
Target Policy
Hardcoded
Sort unit
by kill score (resources cost metric).
Learned
Used the
Borda
count method to give points towards a unit type each time we make a choice.
Parameters machine
learned
from replay data.Slide7
ResultsModel accuracy after learning from more than 1,500 combats extracted from replays (more details in the paper)
Hardcoded
Learned
Sustained Model
0.861
0.848
Decreased
Model
0.905
0.888
Model accuracy and time compared with a low-level model
Accuracy
Time (sec)
Sustained
Model
0.874
0.033
Decreased
Model
0.885
0.039
SparCraft
(AC)
0.8911.681SparCraft (NOK-AV)
0.875
1.358
SparCraft
(KC)
0.850
6.873
Attack Closest
No
OverKill
Attack Value
Kiter
Closest
43 times faster!!!