21
Artificial Intelligence in Game Design Problems and Goals

Artificial Intelligence in Game Design Problems and Goals

Embed Size (px)

Citation preview

Page 1: Artificial Intelligence in Game Design Problems and Goals

Artificial Intelligence in Game Design

Problems and Goals

Page 2: Artificial Intelligence in Game Design Problems and Goals

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

Page 3: Artificial Intelligence in Game Design Problems and Goals

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!

Page 4: Artificial Intelligence in Game Design Problems and Goals

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

Page 5: Artificial Intelligence in Game Design Problems and Goals

Example of Gaming AI

Player coming from unknown direction

Soldier NPC setting up ambush

What to hide behind?

Page 6: Artificial Intelligence in Game Design Problems and Goals

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!

Page 7: Artificial Intelligence in Game Design Problems and Goals

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

Page 8: Artificial Intelligence in Game Design Problems and Goals

Believable NPCs

Intelligent Action:– Good decision making– Realistic movement – Memory of previous actions

(and possibly to improve)– Achieving goals

Page 9: Artificial Intelligence in Game Design Problems and Goals

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”

Page 12: Artificial Intelligence in Game Design Problems and Goals

Game AI Structure

Movement(Action Choice)

“What actions are part of that plan?”

Example: current direction/ speed to reach next point in path

Strategy

“What are my goals?”

Example: Choosing room to move to

Tactics(Decision Making)

“How to accomplish that goal?”

Example: Choosing path to reach room

AI Engine

World Interface/Game State

Animation/Game Physics

Page 13: Artificial Intelligence in Game Design Problems and Goals

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

Page 14: Artificial Intelligence in Game Design Problems and Goals

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

Page 15: Artificial Intelligence in Game Design Problems and Goals

Example of Simplification

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

Page 16: Artificial Intelligence in Game Design Problems and Goals

Example of Simplification

Page 17: Artificial Intelligence in Game Design Problems and Goals

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 learningExample 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

Page 18: Artificial Intelligence in Game Design Problems and Goals

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 < 5 then run away from playerif distance to player < 2 units then attack playerif player visible the run towards playerelse move in random direction

Page 19: Artificial Intelligence in Game Design Problems and Goals

Swarm Intelligence

• Simple NPCs in groups can appear to cooperate

• Decision example:if no other player shooting, I shootif in open, run for cover and shoutif in cover, reload and wait

• Orc motion example:…if NPC blocking path to player then run sidewayselse run towards player…

NPCs appear to be covering one another and coordinating attack!

Page 20: Artificial Intelligence in Game Design Problems and Goals

Swarm Intelligence

• Give each NPC slightly different set of rules to create illusion of personalities

• Example: Pac-Manif distance to player < n then move towards playerelse wander at random

n is different for each ghost!

Large n : appeared “aggressive”

Small n : appeared “mellow”

Page 21: Artificial Intelligence in Game Design Problems and Goals

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