Download presentation
Presentation is loading. Please wait.
1
Robin Hunicke Northwestern University 7.26.04AAAI Workshop Challenges in Game AI AI for Dynamic Difficulty in Games
2
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Early work Interactive installations Stories that users participate in Interacting as expression
3
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Fall 1999 AAAI Narrative Intelligence Symposium Students from Parsons/NYU RE:Play
4
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University The Wheel Set in a prison Rigid structure? Narrative – monolog & notes Factional Actions result in global change Persistence = consequence Consequence = drama!
5
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Too Big Lots of great ideas Erving Goffman Character and Personality Disorders NPR for emotional impact Needed to graduate someday
6
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University 2000 GDC Flexbot Build a mod… “Fix” multiplayer experience
7
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Ghostbot Gladiator fiction Patrons donate items to favorites As long as you have one… …you can live!
8
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Sucked! Bots: “Like White On Rice” Novice players Live longer … seemingly forever
9
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University 2001 Game Design & Tuning Workshop MDA of Multiplayer Challenge Sensation Drama
10
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Oops! Knee-capped multiplayer Removed challenge Rewarded failures Flattened the tension arc …probably easy for experts to “game”
11
Robin Hunicke Northwestern University 7.26.04AAAI Workshop Challenges in Game AI Design Tools at Work
12
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Multiplayer Revisited Fun because it’s people Training up = part of the challenge Frustration is still a factor Why do we keep playing?
13
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Challenge Too Difficult Too Easy Flow Channel Low Skill High Skill increasing skill increasing challenge M. Csikszentmihalyi
14
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Training New tasks Simple Goals Flow Channel Beginner skills Skill increase increasing skill increasing challenge
15
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Tennis Backhand? Beat Your Boss? Flow Channel Hit the ball? Volley for 3 hours in hot sun? increasing skill increasing challenge
16
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Engagement = Cyclical Each challenge = new flow channel trip Understand and control those cycles?
17
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Opponent Process Theory Comfort (steady state) is discouraged Sitting cross-legged “Pins and Needles” Applied to vision, emotion, body chemistry
18
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Solomon & Corbit
19
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Failure Success 10 sec. 10 min. 1 hr. 10 hrs. time
20
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Flux vs. Flow Regulating this feedback Engineering chaos, then calm Keeps the player “engaged”
21
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Game Difficulty Typically static at run-time Flow happens – but only for a niche
22
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Experiencing Flow How can we expand the flow channel? Include “just folks” and “gamers” alike? How can AI help?
23
Robin Hunicke Northwestern University 7.26.04AAAI Workshop Challenges in Game AI Adjusting Game Difficulty
24
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University FPS as a Base Case Obstacle Enemy Search Object Spawn Win (or retreat) Die Fight Find Solve (or not) Get (or not)
25
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Goal Avoid “flailing”: flailing = repeatedly edging towards a state where current means do not support necessary and immediate ends.
26
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Inventory Theory Flow In Flow Out Inventory Level
27
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Health
28
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Health
29
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Health
30
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Basic Steps Notice when a player is flailing Determine which changes can be made Execute changes as seamlessly as possible
31
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University In A Nutshell Look at Player Inventory Current obstacles Performance over time Generate projected probability of failure Adjust accordingly
32
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University AI View of this Process Game Play Session User Model Action Planner observations actions conditions
33
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Dynamic Systems View Game Play Session State Estimator Control Policy observations actions states
34
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Estimation Estimate probability of getting hit Average measurements over time Add a fudge factor to value new estimates over old ones
35
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Control Regulator keeps system within a specified range low varience Tracking System keeps the system within a range that changes over time high varience
36
Robin Hunicke Northwestern University 7.26.04AAAI Workshop Challenges in Game AI And so…
37
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Hamlet Half Life/Case Closed mod Monitor game statistics Predict failure/death Define adjustment actions and policies Execute those actions and policies
38
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Game Chart Some C# and C++ widgets Display data Play session traces “Knobs” to “Frob”
39
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Aesthetic Goals Ramping challenge Responsive reward Sense of mastery
40
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Existing Dynamics Enemies increasing number increasing strength increasing accuracy increasingly variable behavior increasingly “intelligent” or tactical behavior Increased frequency of surprise attacks
41
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Tweakable Mechanics Available health Available ammunition Enemy Type/HP/Accuracy Weapon Type/Strength/Accuracy # of Targets Distance
42
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Other Considerations Terrain/Lighting/Cover Group Movement Player’s Accuracy/Progress Player’s internal state
43
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Two Simple Policies Novice case Expert case Scale between them?
44
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Novice Policy “Comfort Zone” Regulator Babysitter Trial and error Steady supply, consistent demand
45
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Expert Policy “Discomfort Zone” Tracking System Boxing coach or Drill Sergeant Ramping challenge Sporadic supply, high but erratic demand
46
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Could you do better? Best policies? More robust policies? Other factors?
47
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University “Even a little better is better” 10% less work 10% more fun... or both!
48
7.26.04AAAI Workshop Challenges in Game AI Robin Hunicke Northwestern University Thanks Ian & NWU crew Michael, Phoebe and NI/CTP crew Looking Glass Mafia
49
Robin Hunicke Northwestern University 7.26.04AAAI Workshop Challenges in Game AI Questions?
Similar presentations
© 2024 SlidePlayer.com Inc.
All rights reserved.