the intelligence of agents in games - icaart · 2016-07-21 · –they should be able to recover...
TRANSCRIPT
![Page 1: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/1.jpg)
The Intelligence of Agents in Games
Pieter Spronck
Tilburg University, The Netherlands Tilburg center for Cognition and Communication
Creative Computing
![Page 2: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/2.jpg)
![Page 3: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/3.jpg)
0
2
4
6
8
10
12
2000 2002 2004 2006 2008 2010
US Game Sales in Billions of Dollars
![Page 4: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/4.jpg)
![Page 5: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/5.jpg)
![Page 6: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/6.jpg)
![Page 7: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/7.jpg)
![Page 8: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/8.jpg)
![Page 9: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/9.jpg)
![Page 10: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/10.jpg)
![Page 11: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/11.jpg)
Game AI Research
Player interaction
Game
Content Agents
Player Modeling
Search & Planning
AI-assisted Design
Procedural Content Generation
Computational Narrative
General Game AI
Behavior Learning
Believable Agents
![Page 12: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/12.jpg)
Game Agents
![Page 13: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/13.jpg)
![Page 14: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/14.jpg)
Final Fantasy (1987)
![Page 15: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/15.jpg)
Final Fantasy VI (1994)
![Page 16: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/16.jpg)
Final Fantasy VII (1997)
![Page 17: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/17.jpg)
Final Fantasy IX (2001)
![Page 18: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/18.jpg)
Final Fantasy XIII (2009)
![Page 19: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/19.jpg)
Oblivion Buffoon
![Page 20: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/20.jpg)
AI has not changed at all
Ultima VI: The False Prophet (1990)
![Page 21: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/21.jpg)
Game AI Tech Situation
• Game worlds are ever increasing in realism and possibilities • Even keeping old features working is hard
![Page 22: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/22.jpg)
Client Thief
Tourist Vandal Window Shopper Famous Hero Murderer Clown
![Page 23: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/23.jpg)
![Page 24: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/24.jpg)
The Illusion of Natural Behavior
• Smart, to a certain extent • Unpredictable but rational decisions • Emotional influences • Body language to communicate emotions • Being integrated in the environment • Adapting to dynamic circumstances
![Page 25: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/25.jpg)
• No obvious cheating – they should be situated
• Variety – ability to explore new behaviors
• Avoiding stupidity – they should understand their own behavior
• Using the environment – they should understand their environment
• Self-correction – they should be able to recover from mistakes
• Creativity – they should be able to come up with new solutions
Evoking the Illusion
![Page 26: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/26.jpg)
(Online) Adaptive AI
• Self-correction • Creativity • Scalability
![Page 27: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/27.jpg)
Implementing Adaptive Game AI
• High complexity – State-action space
– Uncertainty
– Real-time
• Computational reqs. – Speed
– Effectiveness
– Robustness
– Efficiency
• Functional reqs. – Clarity
– Variety
– Consistency
– Scalability
![Page 28: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/28.jpg)
Dynamic Scripting
AI team human- controlled team
Knowledge
Base A
Knowledge
Base B
generate script
generate script
Script A
Script B
script control
script control
human control
human control
weight updates
Combat
![Page 29: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/29.jpg)
Simulated CRPG Situation
![Page 30: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/30.jpg)
Typical Fitness Progression
• Absolute
• Average over last 10 encounters
"turning point"
![Page 31: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/31.jpg)
0
50
100
150
200
Offensive Disabling Cursing Defensive Rnd.team Rnd.agent Consec.
Monte Carlo Dynamic scripting Biased Rulebases
![Page 32: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/32.jpg)
Basic Setup
![Page 33: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/33.jpg)
Why Does Dynamic Scripting Work?
• Scripts are readable (clarity) • Scripts are always different (variety) • Script creation is almost instantaneous (speed) • Knowledge base avoids bad behavior (effectiveness) • Redistribution of weights allows knowledge to return even if it
was discarded before (robustness) • Every trial is used for adaptation (efficiency)
• Exploration and exploitation happen simultaneously
![Page 34: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/34.jpg)
• AI should be able to play stronger than the human player • AI should adapt to the level of skill of the human player • AI should constantly offer new challenges
![Page 35: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/35.jpg)
Optimisation
0
5
10
15
0 10 20 30 40 50 60 70 80 90 100
Top Culling
0
5
10
15
0 10 20 30 40 50 60 70 80 90 100
![Page 36: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/36.jpg)
![Page 37: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/37.jpg)
![Page 38: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/38.jpg)
Game AI Game World
Human Player
Player Model
Actions Preferences
Style Personality
Skills
actions
actions
observations
observations predictions updates
similarity?
biometrics?
Player Modeling
![Page 39: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/39.jpg)
Recent Work
• David Thue’s PaSSAGE
![Page 40: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/40.jpg)
![Page 41: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/41.jpg)
![Page 42: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/42.jpg)
Costa McCrae
![Page 43: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/43.jpg)
![Page 44: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/44.jpg)
![Page 45: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/45.jpg)
![Page 46: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/46.jpg)
![Page 47: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/47.jpg)
![Page 48: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/48.jpg)
Some Findings
• High Openness correlates with fast choices and movement • High Conscientiousness correlates with ethical decisions • High Agreeableness correlates with friendly behavior • High Neuroticism correlates with taking long to finish
![Page 49: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/49.jpg)
• First 45 minutes • 165 variables
– 107 conversation
– 37 G.O.A.T.
– 20 movement
– 1 miscellaneous
![Page 50: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/50.jpg)
Neverwinter Nights: 80 test subjects
Fallout 3: 37 test subjects
![Page 51: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/51.jpg)
![Page 52: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/52.jpg)
Collected Data: 1. Player name 2. 100-item IPIP 3. Age 4. Country of residence 5. Gaming platform 6. Credits
![Page 53: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/53.jpg)
Personality and play style: - Conscientiousness relates to speed - Unlock score relates to multiple personality dimensions - Work ethic relates to performance
![Page 54: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/54.jpg)
• Age explains ~45% of variance in play style • Older players focus more on the game's goals • Older players are less successful at achieving the game's goals • For most play style variables, players peak around 20 • Effect sizes are very high for age groups
![Page 55: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/55.jpg)
![Page 56: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/56.jpg)
Conclusions
![Page 57: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/57.jpg)
![Page 58: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/58.jpg)
![Page 59: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/59.jpg)
![Page 60: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/60.jpg)
People Involved in the Research
• Prof.dr. Jaap van den Herik • Prof.dr. Eric Postma • Prof.dr. Arnout Arntz • Dr. Sander Bakkes • Dr. Marc Ponsen • Dr. Giel van Lankveld • Shoshannah Tekofsky, MSc
![Page 61: The Intelligence of Agents in Games - ICAART · 2016-07-21 · –they should be able to recover from mistakes • Creativity –they should be able to come up with new solutions](https://reader031.vdocuments.site/reader031/viewer/2022011912/5fa0fcbbf70ae233bd27d749/html5/thumbnails/61.jpg)
References • Pieter Spronck, Marc Ponsen, Ida Sprinkhuizen-Kuyper, and Eric Postma
(2006). “Adaptive Game AI with Dynamic Scripting.” Machine Learning, Vol. 63, No. 3, pp. 217–248.
• Marc Ponsen, Héctor Muñoz-Avila, Pieter Spronck, and David W. Aha (2006). Automatically Generating Game Tactics with Evolutionary Learning. AI Magazine, Vol.27, No. 3, pp.75–84.
• Giel van Lankveld, Pieter Spronck, Jaap van den Herik, and Arnoud Arntz (2011). "Games as Personality Profiling Tools." 2011 IEEE Conference on Computational Intelligence in Games (CIG'11), pp. 197–202.
• Sander Bakkes, Pieter Spronck, and Giel van Lankveld (2012). Player Behavioral Modelling for Video Games. Entertainment Computing, Vol. 3, Nr. 3, pp. 71–79.
• Shoshannah Tekofsky, Pieter Spronck, Aske Plaat, Jaap van den Herik, and Jan Broersen (2013). PsyOps: Personality Assessment Through Gaming Behavior. Proceedings of the 2013 Foundations of Digital Games Conference.
• Shoshannah Tekofsky, Pieter Spronck, Aske Plaat, Jaap van den Herik, and Jan Broersen (2013). Play Style: Showing Your Age. 2013 IEEE Conference on Computational Intelligence in Games (CIG), pp. 177–184. IEEE Press.