Transcript Presentation

Michael Hercenberg

What is Dynamic Learning?


Why?




Leaning in real-time
Replaces hardcoded scripts
More ‘human’ game opponents
More suitable environments
Other aspects have advanced greatly
Graphics
 Voicing
 Music
 Controls


80’s



90’s



Move left, then right
Wait for player
Search-and-Destroy
Player-like Enemies
00’s


Small advances
Loopholes

Data Mining

Uses data to create next level or
encounter
 Pro: Drastically alter the world
 Con: Needs data and time

Difficulty Scaling

Makes changes in
real-time
 Pro: Makes corrections
when needed
 Con: Running real-time
can be a strain

Explicit Context
Tracking

‘Windowed’ Data
Mining

Dynamic Choice Making


Introduce this into an RPG (Role-Playing Game)
Choices made drastically change the story

Not just give an alternate ending
Choice
Interactions
Environment