19
Embracing Emergent Behavior with Goal- Based AI Kevin Dill [email protected]

Embracing Emergent Behavior with Goal-Based AI Kevin Dill [email protected]

  • View
    241

  • Download
    0

Embed Size (px)

Citation preview

Page 1: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Embracing Emergent Behavior with Goal-Based AI

Kevin Dill

[email protected]

Page 2: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Blue Fang Games

“To create compelling, emotionally engaging games, focused on the animal kingdom, that set the benchmark for broad-based family entertainment.”

Page 3: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com
Page 4: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

The Plan• Motivation

• Kohan 2 Demo

• Common AI Techniques

• Goal-based AI

• Boxy-dog Demo

• Questions

Page 5: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

The Plan• What I Want:

– Cunning Opponents– Responsive Allies– Replayability– Organic Credibility – Emotional Appeal– Compelling Performances

• Or, more generally:– Situational Awareness– Emergent Behavior

Page 6: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Motivation, cont.• Declarative AI (vs. Procedural AI)

– Wikipedia: A program is “declarative” if it describes what something is like, rather than how to create it.

– Developers role: not to tell the AI what to do, but to tell the AI how to decide for itself.

Page 7: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com
Page 8: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Techniques – Scripted AI• AI Follows a script, much like a movie

– Script specifies exactly what will happen, when it will happen, where it will happen

• Advantages:– Gives designers explicit control – Easy to write– Easy to balance

• Disadvantages– Repetitive and predictable

Page 9: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Techniques – State Machines• A “state” is defined for every high-level

action the AI can take

• Transitions are defined to move from one state to another state

• Each state has custom code to control the character while in that state

Page 10: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

First Person Shooter Example

Get Ammo

Get Health

Run Away

Search For Enemy

Attack

Ene

my

Fou

nd

Enem

yLost

Low on A

mm

oLow

on

Hea

lth

Got

Aw

ay,

Low

on

Hea

lth

Got

Hea

lth

Got Ammo

Got

Aw

ay,

Low

on

Am

mo

Page 11: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Techniques – State Machines• Advantages:

– Easy to conceptualize– Easy to implement– Middleware tools exist

• Disadvantages:– Complexity scales poorly as AI grows– Rampant duplication of code– Can only do one thing at a time

Page 12: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Techniques – Goal Based AI• A “goal” is defined for every high-level

action that the AI can take

• Each goal is assigned a priority:– Base priority (evaluate current situation)– Allocate resources– Optimize resources and calculate final priority

• Highest priority goal(s) are executed

Page 13: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Goal Types• Some common RTS goals:

– Attack – Construct Building– Defend – Repair Building– Explore – Upgrade Building– Recruit Unit – Sell Building– Recover Health – Give Resources To Ally– Research

Page 14: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Techniques – Goal Based AI• Advantages

– Flexible and powerful– Complexity scales fairly well as AI grows– Can execute more than one goal at a time– Emergent behavior

• Disadvantages:– Priority calculations (“Bucket of Floats”)– Emergent behavior

Page 15: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Goal Selection Basics• WWHD (What Would a Human Do?)

– Write down a list of the factors you would consider if you were playing the game

• Some common tricks:– Bonuses – Repeat Penalties– Multipliers – One-Time Bonuses– Exponents – Actor Categories– Fuzzy Factors – Templates

Page 16: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Example: Attack Goal• Base priority:

– Actor value for the most desirable building or unit in the area (taking into account enemy’s economy if appropriate)

– Travel Distance– Intervening targets (attack goals only)

Page 17: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Attack Goal, cont.• Priority Curve:

– Target CV ratio– Min CV to assign– Low CV exponent – Max advantage– Max multiplier

• Other considerations– Combined arms– Wall strength– Adjusting builder CV

My CV / Enemy CV

1.2 3.0

Mul

tiplie

r

1x

2x

Target CV Ratio

* CV = Combat Value

Page 18: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Loose Ends• Goal Commitment

– IF: you can’t afford something now– BUT: you will be able to soon– THEN: don’t perform lower priority goals that

use the same resource

• Goal Inertia– Bonus to keep doing what you’re doing

• Locked Goals– Disable all other goals until current goal is

complete

Page 19: Embracing Emergent Behavior with Goal-Based AI Kevin Dill kad@bluefang.com

Jack the Terrier