Artificial Intelligence in Game Design

1
Artificial Intelligence in Game Design

• Problems and Goals

2
AI vs. Gaming AI

• Standard Artificial Intelligence
• Expert Systems
• Probabilistic/Fuzzy Logic
• Robotics
• Machine Learning
• Goal Finding best solution to some problem
• Characteristics
• Expensive and time consuming to develop
• Large number of processing cycles to run

3
AI vs. Gaming AI

• Example Chess (Deep Blue, IBM)
• MINMAX algorithm
• Heuristic knowledge
• Databases of opening moves, endgames
• Result
• Played at world champion level (best solution)
• Took several minutes per move (ok in chess)
• Not viable as commercial chess game!

4
Goals of Gaming AI

• Challenging but beatable
• Intelligence level artificially limited
• AI not given all information
• Problem making AI intelligent enough!
• Players find and take advantage of limitations
• Cheats compensate for bad AI

5
Example of Gaming AI
Soldier NPC setting up ambush
Player coming from unknown direction
What to hide behind?
6
Example of Gaming AI

• Choose at random?
• Current location of player?
• Base on realistic criteria
• Terrain around soldier
• Past player actions, etc.
• This is most difficult approach!

7
Believable NPCs

• Opponents that offer challenge
• Orc characters should move realistically
• Boss characters should appear as intelligent as
  player
• Minions that require little micromanaging
• Other characters interesting to interact with

8
Believable NPCs

• Intelligent Action
• Good decision making
• Realistic movement
• Memory of previous actions (and possibly to
  improve)
• Achieving goals

9
Believable NPCs

• Believable as Characters
• Acts like human (or orc, dog, etc.)
• Has appropriate emotional states
• Does not always behave predictably
• Can interact with player
• Major simplification from standard AI
  NPCs restricted to limited domain
• Example Shopkeeper

10
Turing Test

• Turing test for AI

11
Turing Test for AI Gaming

• Does NPC act appropriately for its role in game?
• Does it act intelligently?
• Does it appear to have appropriate information?
• Does it behave with the personality we would
  expect?

vs.
12
Game AI Structure
Strategy
What are my goals? Example Choosing room to
move to
World Interface/ Game State
How to accomplish that goal? Example Choosing
path to reach room
Tactics (Decision Making)
Animation/ Game Physics
Movement (Action Choice)
What actions are part of that plan? Example
current direction/ speed to reach next point in
path
AI Engine
13
Constraints on Gaming AI

• Efficiency
• Must consume few processor cycles
• Must often act in real time
• Football, racing, etc.
• Simple approaches usually best
• Choose fast over optimal
• Tweak game to support AI
• Depend on player perceptions

14
Tradeoffs

• Optimal solutions require complex algorithms
• Shortest path ? O(n2)
• Optimal plan ? Exponential tree size
• Many games use greedy algorithms
• Choose action resulting in minimal distance to
  goal
• O(n) time

15
Example of Simplification

• Pac-Man
• Algorithm Ghosts move towards player
• Problem ghosts stuck in cul-de-sacs

16
Example of Simplification
17
Black and White Game

• Creature trained by player by observing player
  actions in different situations
• Later in game creature takes same actions
• Based entirely on decision tree learning

Example Allegiance Defense Tribe Attack
1 friendly weak Celtic no
2 enemy weak Celtic yes
3 friendly strong Norse no
4 enemy strong Norse no
5 friendly weak Greek no
6 enemy medium Greek yes
7 enemy strong Greek no
8 enemy medium Aztec yes
9 friendly weak Aztec no
18
Apparent Intelligence

• NPCs can appear intelligent to player even if
  based on simple rules
• Theory of mind
• We tend to ascribe motives/decision
• making skills similar to our own to
• other entities, whether this is actually
• happening or not!

if hitPoints lt 5 then run away from playerif
distance to player lt 2 units then attack
playerif player visible the run towards
playerelse move in random direction
19
Swarm Intelligence

• Simple NPCs in groups can appear to cooperate
• Decision exampleif no other player shooting, I
  shootif in open, run for cover and shoutif in
  cover, reload and wait
• Orc motion exampleif NPC blocking path to
  player then run sidewayselse run towards
  player

NPCs appear to be covering one another and
coordinating attack!
20
Swarm Intelligence

• Give each NPC slightly different set of rules to
  create illusion of personalities
• Example Pac-Manif distance to player lt n
  then move towards playerelse wander at random

n is different for each ghost!
Large n appeared aggressive
Small n appeared mellow
21
Role of Traditional AI

• Good decision making
• Acts like human (or orc, dog, etc.)
• Avoids predictability
• Realistic movement
• Evasion/pursuit of player
• Choosing paths through complex terrain
• Cooperation among groups
• Memory of previous actions
• Achieving goals

Decision Trees Finite State Machines Random/Fuzzy
Machines
Robotics
Swarm Intelligence
Simple Iterative Learning
Goal-based Planning