Why AI Is Shaping our games - Johanna Pirker, 2019

Johanna Pirker
Johanna Pirker@ Graz University of Technology at Graz University of Technology
S C I E N C E * PA S S I O N * T E C H N O L O G Y
WHY AI IS SHAPING OUR GAMES
D R . J O H A N N A P I R K E R , T U G R A Z , A U S T R I A
L U D I C I O U S 2 0 1 9
JOHANNA PIRKER
▸ Computer Scientist & Software Engineering @Graz University of Technology
▸ Virtual Realities (Maroon) @Massachusetts Institute of Technology
▸ Research & Edu at Institute for Interactive Systems & Data Science, @TUGraz
▸ Virtual Realities & Worlds
▸ HCI, E-Learning, UX, Data Analysis (SNA)
▸ Games Education (for CS) & 

Research, Design, Development & Analysis
▸ GUR Consulting @BetterChaos
▸ Website: www.jpirker.com
@JOEYPRINK
Why AI Is Shaping our games - Johanna Pirker, 2019
AI MIRACLES..
“MAKING COMPUTERS ACT LIKE THEY DO IN THE MOVIES.”
1. THE CAPABILITY OF A MACHINE TO IMITATE
INTELLIGENT HUMAN BEHAVIOR.

2. A BRANCH OF COMPUTER SCIENCE DEALING WITH THE
SIMULATION OF INTELLIGENT BEHAVIOR IN COMPUTERS.
Merriam-Webster defines artificial intelligence this way.
“REAL” AI
▸ 1. learn over time in response to changes in its
environments
▸ (e.g. Netflix recommendations but not Twitter
black lists)
▸ 2. what it learns should be interesting enough that it
would take humans some effort to learn
▸ (Turing test)
Why AI Is Shaping our games - Johanna Pirker, 2019
AI IN GAMES
▸ … generate responsive, adaptive, & intelligent behaviour
▸ uses path finding, decision trees, data mining, PCG, …
▸ usually do not facilitate computer learning
▸ -> predetermined & limited set of responses to a limited set of inputs
▸ ILLUSION OF INTELLIGENCE
▸ good gameplay without environment restrictions
▸ learn & use from “real AI” strategies
▸ Learning Tamagotchi
▸ decision trees (scripting)
▸ -> AI stupidity, predictive behaviour, loss of immersion
▸ pathfinding
▸ (Half Life, “Crouch Cover”)
▸ NPC behaviour in Doom
▸ NPCs fighting NPCs
AI IN GAMES - ISSUES
PLAY
GAMES.
CONTRIBUTE
CONTENT.
DESIGN

GAMES.
UNDERSTAND 

PLAYERS.
I. PLAY GAMES.
AI TO PLAY GAMES
ROBOCUP
AI TO PLAY GAMES
CHESS - IBM DEEP BLUE VS. GARRY KASPAROV (1997)
 "I could feel — I could smell — a new kind of intelligence across the table,"
AI TO PLAY GAMES
JEOPARDY! - IBM WATSON VS. KEN JENNINGS (2011)
 "I could feel — I could smell — a new kind of intelligence across the table,"
AI TO PLAY GAMES
GO - GOOGLE ALPHAGO (DEEPMIND) VS. LEE SEDOL (2016)
AI TO PLAY GAMES
DEEPMIND VS. STARCRAFT II (2019)
AI TO PLAY GAMES
http://gameaibook.org/book.pdf
▸ Chess Two-player adversarial, deterministic, fully observable,
branching factor ~35, ~70 turns
▸ Go Two-player adversarial, deterministic, fully observable, branching
factor ~350, ~150 turns
▸ Frogger (Atari 2600) 1 player, deterministic, fully observable, bf 6,
hundreds of ticks
▸ Halo 1.5 player, deterministic, partially observable, bf ???, tens of
thousands of ticks
▸ Starcraft 2-4 players, stochastic, partially observable, bf > a million,
tens of thousands of ticks
▸ Togelius
AI TO PLAY GAMES
AI TO PLAY GAMES
TRAIN AI HOW TO PLAY SNAKE (DEEP REINFORCEMENT LEARNING)
On the left, the agent was not trained and had no clues on what to do whatsoever. The game on the right
refers to the game after 100 iterations (about 5 minutes). The highest score was 83 points, after 200
iterations.
https://github.com/maurock/snake-ga
AI TO PLAY GAMES
TRAIN AI HOW TO PLAY STARCRAFT
‣ A Machine Learning API developed by Blizzard that gives researchers and developers hooks into the game.
‣ A dataset of half a million anonymised game replays,.  
‣ An open source version of DeepMind’s toolset, PySC2
‣ A series of simple RL mini-games to test the performance of agents on specific tasks.
https://deepmind.com/blog/deepmind-and-blizzard-open-starcraft-ii-ai-research-environment/
AI TO PLAY GAMES
WHY USE AI TO PLAY GAMES?
▸ Playing to win vs playing for experience
▸ For experience: human-like, fun, predictable…?
▸ Playing in the player role vs playing in a non-player role
http://gameaibook.org/book.pdf
METHODS
▸ Planning-Based
▸ Uninformed search (e.g. BFS),Informed search (e.g. A*),
Evolutionary algorithms
▸ Reinforcement learning (training time)
▸ TD-learning / approximate dynamic programming,
Evolutionary algorithms
▸ Supervised learning (requires play traces to learn from)
▸ Neural nets, k-nearest neighbors etc
▸ Random (requires nothing)
AI TO PLAY GAMES
▸ Togelius
II. CONTRIBUTE CONTENT.
CONTRIBUTE CONTENT
PROCEDURAL CONTENT GENERATION
CONTRIBUTE CONTENT
PROCEDURAL CONTENT GENERATION
CONTRIBUTE CONTENT
PROCEDURAL CONTENT GENERATION
CONTRIBUTE CONTENT
PROCEDURAL CONTENT GENERATION
• Artistic aspects
• Corner-cases
• Lack of complete control
• Depends on the content
• Client-side calculations?
• Replayable content?
• Cheap
• Lots of content
• Dynamic Reaction on player
• Reduce burden of artist
• Save memory
• Large worlds
• Replayable content
• http://pcg.wikidot.com/category-pcg-algorithms
METHODS
▸ Search-Based Methods
▸ Solver-Based Methods
▸ Grammar-Based Methods
▸ Cellular Automata
▸ Noise and Fractals
▸ Machine Learning
CONTRIBUTE CONTENT
GENERATE CONTENT FOR…
▸ Environments (Random Maps, Random Dungeons)
▸ Generative Art and models
▸ Textures
▸ Music
▸ Story
▸ Gameplay
CONTRIBUTE CONTENT
III. UNDERSTAND PLAYERS
PLAYER MODELING
PLAYER MODELING
▸ … detection, prediction and expression of human player
characteristics that are manifested through cognitive,
affective and behavioral patterns while playing games
▸ can be used to dynamically adjust the gameplay (dynamic
difficult adjustment)
BEHAVIOURAL PROFILING
B A R T L E ’ S G A M E R T Y P E S
http://www.gamerdna.com/quizzes/bartle-test-of-gamer-psychology
Story	
Story	Enjoyer	
Party	Player	
Killer		
Online	Hero	
Allrounder	
0%	 20%	 40%	 60%	 80%	 100%	
Story	Enjoyer	
Party	Player	
Killer		
Online	Hero	
Allrounder	
Time	spent	
Story	
Campaign	
Arena	
Online	MulAplayer	
Local	MulAplayer	
P L AY E R H A B I T ( P L AY E R F I N G E R P R I N T )
P L AY E R P R O F I L E S I N F O R Z A
• What Drives People: Creating Engagement Profiles of
Players from Game Log Data
• 120 mio race entries from 1.2 mil players
•
Harpstead, E., Zimmermann, T., Nagapan, N., Guajardo, J. J., Cooper, R., Solberg, T., & Greenawalt, D. (2015, October). What Drives People: Creating Engagement Profiles of Players from Game Log Data. In Proceedings of the
2015 Annual Symposium on Computer-Human Interaction in Play (pp. 369-379). ACM.
F L O W ( M I H A LY C S I K S Z E N T M I H A LY I )
HOW PLAYSTYLES EVOLVE:
PROGRESSION ANALYSIS AND
PROFILING IN JUST CAUSE 2
https://link.springer.com/chapter/10.1007/978-3-319-46100-7_8
F E AT U R E S
• Spatio-temporal navigation
• combat performance
• progression through the main storyline
• side quests..
• Agency missions (+ reach specific level of Chaos)
• subset of features based on the core mechanics
• -> does not impact the analytical framework
• -> impacts the kinds of conclusions that can be derived
P L AY E R P R O G R E S S I O N A L O N G T H E
M I S S I O N S
R E S U LT S
• How can we describe player behaviour of the
different player profiles?
P L AY E R B E H AV I O U R A L O N G T H E
S T O RY L I N E
jpirker.com/jc2/aaSankey.html
G O A L S
• Improve our understanding of the different player
behaviours and factors to improve engagement
• Find issues to avoid drop-outs
• Provide tools for game designers to (visually)
analyse the game and improve the understanding
of players
• Find game design flaws early and automatically
IV. DESIGN GAMES
AI AS A PART OF
GAME DESIGN!!!!
AI TO DESIGN GAMES
ROLES OF AI IN GAMES
▸ AI in the foreground of games - Foregrounding AI
▸ create gameplay based around thinking about how agents
work
▸ Designing games that use AI techniques in a new way as a
core of their gameplay
https://medium.com/@mtrc/tombs-of-tomeria-7c2e800a6511
Mike Treanor, Alexander Zook, Mirjam P Eladhari, Julian Togelius, Gillian Smith, Michael Cook, Tommy Thompson, Brian
Magerko, John Levine and Adam Smith: AI-Based Game Design Patterns. Computational Creativity and Games Workshop,
2015.
AI-BASED GAME DESIGN
▸ Game design strategies/rules described when AI still
“young” and most games are designed to not need AI
▸ Game designers often claim that AI won’t make games
better
▸ Our goal: show where AI can be used, show alternative
routes
▸ we need to design new games from scratch based on
new design principles
Mike Treanor, Alexander Zook, Mirjam P Eladhari, Julian Togelius, Gillian Smith, Michael Cook, Tommy Thompson, Brian
Magerko, John Levine and Adam Smith: AI-Based Game Design Patterns. Computational Creativity and Games Workshop,
2015.
AI TO DESIGN GAMES
AI GAME DESIGN PATTERNS
Mike Treanor, Alexander Zook, Mirjam P Eladhari, Julian Togelius, Gillian Smith, Michael Cook, Tommy Thompson, Brian
Magerko, John Levine and Adam Smith: AI-Based Game Design Patterns. Computational Creativity and Games Workshop,
2015.
AI TO DESIGN GAMES
AI DESIGN PATTERNS
1 AI IS VISUALIZED
▸ Pattern: Provide a visual representation of the underlying AI state, making gameplay revolve around
explicit manipulation of the AI state.
▸ Example: Third Eye Crime is a stealth game that illustrates this pattern by visualizing the guard AI position
tracking and estimation system. Gameplay involves avoiding guards or throwing distractions to manipulate
the guards’ predictions of player location. The direct visualization of AI state allows a designer to build a
game around manipulating, understanding, and mentally modeling how the AI state changes.
2 AI AS ROLE-MODEL
▸ Pattern: Provide one or more AI agents for the player to behave similarly to.
▸ Example: Spy Party is a game where one player is a spy at a party populated by FSM agents and the
opposing player is a sniper watching the party with a single shot to kill the spy. Gameplay for the
spy centers on the player attempting to act similarly to the party agents while discreetly performing
tasks in the environment like planting a bug or reading a code from a book.
AI DESIGN PATTERNS
3 AI AS TRAINEE
▸ Pattern: Have player actions train an AI agent to perform tasks central to gameplay.
▸ Example: Black & White is a god game where the player trains a creature to act as
an autonomous assistant in spatial regions where the player cannot take direct
action. The creature learns sets of behaviors through a reward signal based on a
needs model; the creature also takes direct feedback through player action (e.g.,
slapping or petting the creature after it takes actions).
AI DESIGN PATTERNS
4 AI IS EDITABLE
▸ Pattern: Have the player directly change elements of an AI agent that is central to gameplay.
▸ Example: Galactic Arms Race is a space shooter where how the player uses different weapons evolves an underlying neural
network representation to change weapon firing behavior. Base gameplay revolves around finding a set of firing behaviors that
together enable a player to succeed at destroying opposition (another example of the AI as Trainee pattern). One gameplay mode
allows the player to explicitly manipulate the network weights on weapons, allowing more precise control over the firing patterns
of the evolved weapons. This control enables players to more finely explore the space of parameterizations, leading to an indirect
way to understand the processes of the AI system.
Erin J. Hastings, Ratan K. Guha, and Kenneth O. Stanley (2009)
Automatic Content Generation in the Galactic Arms Race Video Game
In: IEEE Transactions on Computational Intelligence and AI in Games, volume 1, number 4, pages 245-263, New York: IEEE Press, 2009. (Manuscript 19 pages)
AI DESIGN PATTERNS
5 AI IS GUIDED
▸ Pattern: The player assists a simple or brittle AI agent that is threatened with self-destruction.
▸ Example: The Sims addressed the problem of “human-like” agents in a social world by making
gameplay revolve around the player addressing the needs of simple agents. AI agents have a set of
needs and desires they attempt to pursue while players intervene to provide for the needs of the
agents through food, shelter, work, socialization, and eventually more grand life aspirations. By having
players care for the AI, players come to (at least indirectly) model some of the processes used by the AI.
AI DESIGN PATTERNS
8 AI AS VILLAIN
▸ Pattern: Require players to complete a task or overcome an AI opponent where the AI is aiming to create an
experience (e.g., tension or excitement) rather than defeat the player.
▸ Example: Alien: Isolation is a first-person survival horror game where the opposing alien was designed to harass
the player without using an optimal strategy that would always kill the player directly. The enemy alien spends
the game hunting the player, displaying behaviors of seeking the player’s location (a weak version of AI is
Visualized), and gradually learning from tactics the player uses repeatedly (an oppositional application of AI as
Trainee). By having players continually reason on what the alien has learned and where it will go the player is
forced to consider the state of the AI and (after repeated play) the processes involved in the AI learning.
AI DESIGN PATTERNS
AI TO CREATE
GAMES!!!!
Why AI Is Shaping our games - Johanna Pirker, 2019
Why AI Is Shaping our games - Johanna Pirker, 2019
AI TO DESIGN GAMES /
COMPUTATIONAL
CREATIVITY
RESOURCES
▸ IEEE Computational Intelligence and Games (CIG)
▸ AAAI Artificial Intelligence in Interactive Digital
Entertainment (AIIDE)
▸ Foundations of Digital Games (FDG)
▸ IEEE Transactions on Games (ToG)
▸ Yannakakis and Togelius: Artificial Intelligence and Games
www.gameaibook.org
THANK YOU FOR YOUR
ATTENTION.
JOHANNA PIRKER, JPIRKER@MIT.EDU, @JOEYPRINK


Further information:
jpirker.com
This is how others play your game!
1 of 60

Recommended

Know your player - Optimizing the player experience by
Know your player - Optimizing the player experienceKnow your player - Optimizing the player experience
Know your player - Optimizing the player experienceJohanna Pirker
6.7K views57 slides
Games User Research & User Testing 101 by
Games User Research & User Testing 101Games User Research & User Testing 101
Games User Research & User Testing 101Johanna Pirker
6.5K views26 slides
Group Forming Processes - Experiences and Best Practice from Different Game Jams by
Group Forming Processes - Experiences and Best Practice from Different Game JamsGroup Forming Processes - Experiences and Best Practice from Different Game Jams
Group Forming Processes - Experiences and Best Practice from Different Game JamsJohanna Pirker
6.2K views28 slides
Post Game Jam: What's Next? by
Post Game Jam: What's Next? Post Game Jam: What's Next?
Post Game Jam: What's Next? Johanna Pirker
6.1K views42 slides
Virtual Environments for 3D Visualisations by
Virtual Environments for 3D VisualisationsVirtual Environments for 3D Visualisations
Virtual Environments for 3D VisualisationsJohanna Pirker
9.3K views27 slides
How Playstyles Evolve: Progression Analysis and Profiling in Just Cause 2 by
How Playstyles Evolve: Progression Analysis and Profiling in Just Cause 2How Playstyles Evolve: Progression Analysis and Profiling in Just Cause 2
How Playstyles Evolve: Progression Analysis and Profiling in Just Cause 2Johanna Pirker
4.9K views23 slides

More Related Content

What's hot

Exploratory and Collaborative Learning - Experience in Immersive Environments by
Exploratory and Collaborative Learning - Experience in Immersive EnvironmentsExploratory and Collaborative Learning - Experience in Immersive Environments
Exploratory and Collaborative Learning - Experience in Immersive EnvironmentsJohanna Pirker
5K views29 slides
Level Up - Everything you need to know about search, you learned playing vide... by
Level Up - Everything you need to know about search, you learned playing vide...Level Up - Everything you need to know about search, you learned playing vide...
Level Up - Everything you need to know about search, you learned playing vide...Lucidworks
1.4K views28 slides
Let's put the right questions by
Let's put the right questionsLet's put the right questions
Let's put the right questionsAndreea-Zenovia Popescu
516 views40 slides
Usabilty workshop, Cluj Napoca by
Usabilty workshop, Cluj NapocaUsabilty workshop, Cluj Napoca
Usabilty workshop, Cluj NapocaAndreea-Zenovia Popescu
495 views11 slides
Bleed in, Bleed Out – A Design Case in Board Game Therapy by
Bleed in, Bleed Out – A Design Case in Board Game TherapyBleed in, Bleed Out – A Design Case in Board Game Therapy
Bleed in, Bleed Out – A Design Case in Board Game TherapyMirjam Eladhari
897 views27 slides
Game Analysis at HEVGA PhD Summer School by
Game Analysis at HEVGA PhD Summer SchoolGame Analysis at HEVGA PhD Summer School
Game Analysis at HEVGA PhD Summer SchoolPetri Lankoski
2.4K views28 slides

What's hot(20)

Exploratory and Collaborative Learning - Experience in Immersive Environments by Johanna Pirker
Exploratory and Collaborative Learning - Experience in Immersive EnvironmentsExploratory and Collaborative Learning - Experience in Immersive Environments
Exploratory and Collaborative Learning - Experience in Immersive Environments
Johanna Pirker5K views
Level Up - Everything you need to know about search, you learned playing vide... by Lucidworks
Level Up - Everything you need to know about search, you learned playing vide...Level Up - Everything you need to know about search, you learned playing vide...
Level Up - Everything you need to know about search, you learned playing vide...
Lucidworks1.4K views
Bleed in, Bleed Out – A Design Case in Board Game Therapy by Mirjam Eladhari
Bleed in, Bleed Out – A Design Case in Board Game TherapyBleed in, Bleed Out – A Design Case in Board Game Therapy
Bleed in, Bleed Out – A Design Case in Board Game Therapy
Mirjam Eladhari897 views
Game Analysis at HEVGA PhD Summer School by Petri Lankoski
Game Analysis at HEVGA PhD Summer SchoolGame Analysis at HEVGA PhD Summer School
Game Analysis at HEVGA PhD Summer School
Petri Lankoski2.4K views
Four ways game research field approach narrative by Mirjam Eladhari
Four ways game research field approach narrativeFour ways game research field approach narrative
Four ways game research field approach narrative
Mirjam Eladhari2.1K views
FigureRunning for Health by Willempje
FigureRunning for HealthFigureRunning for Health
FigureRunning for Health
Willempje180 views
コンピューターと対話する - Conversation as a platform - by Daiyu Hatakeyama
コンピューターと対話する - Conversation as a platform -コンピューターと対話する - Conversation as a platform -
コンピューターと対話する - Conversation as a platform -
Daiyu Hatakeyama639 views
4. interactive proposal (1) by OliverFrost4
4. interactive proposal (1)4. interactive proposal (1)
4. interactive proposal (1)
OliverFrost429 views
TOG: An Innovation Centric Approach to teaching Computational Expression and ... by Mirjam Eladhari
TOG: An Innovation Centric Approach to teaching Computational Expression and ...TOG: An Innovation Centric Approach to teaching Computational Expression and ...
TOG: An Innovation Centric Approach to teaching Computational Expression and ...
Mirjam Eladhari2.4K views
Fares Kayali - ARGs, Persuasion in Context by Fares Kayali
Fares Kayali - ARGs, Persuasion in ContextFares Kayali - ARGs, Persuasion in Context
Fares Kayali - ARGs, Persuasion in Context
Fares Kayali978 views
Planning (done) by AllanGodin
Planning (done)Planning (done)
Planning (done)
AllanGodin46 views
How to ditch meetings and play games instead by Neil Turner
How to ditch meetings and play games insteadHow to ditch meetings and play games instead
How to ditch meetings and play games instead
Neil Turner8.8K views
2. research(radio) by Josh Ruff
2. research(radio)2. research(radio)
2. research(radio)
Josh Ruff69 views
aag_2016_2026_rr by John Solly
aag_2016_2026_rraag_2016_2026_rr
aag_2016_2026_rr
John Solly202 views

Similar to Why AI Is Shaping our games - Johanna Pirker, 2019

Why AI is shaping our games by
Why AI is shaping our gamesWhy AI is shaping our games
Why AI is shaping our gamesFörderverein Technische Fakultät
1.3K views65 slides
Artificial intelligence by
Artificial intelligenceArtificial intelligence
Artificial intelligencesabairshad4
150 views17 slides
2021 - We are Developers - How Data is Shaping our Games by
2021 - We are Developers - How Data is Shaping our Games2021 - We are Developers - How Data is Shaping our Games
2021 - We are Developers - How Data is Shaping our GamesJohanna Pirker
70 views63 slides
9.5 Theses on the Power and Efficacy of Gamification by
9.5 Theses on the Power and Efficacy of Gamification9.5 Theses on the Power and Efficacy of Gamification
9.5 Theses on the Power and Efficacy of GamificationSebastian Deterding
3.7K views134 slides
Artificial Intelligence in Gaming by
Artificial Intelligence in GamingArtificial Intelligence in Gaming
Artificial Intelligence in GamingAnmol Sawhney
1.1K views16 slides
"The Perspective Game: An Epistemic Game for Civic Engagement" by Sherry Jone... by
"The Perspective Game: An Epistemic Game for Civic Engagement" by Sherry Jone..."The Perspective Game: An Epistemic Game for Civic Engagement" by Sherry Jone...
"The Perspective Game: An Epistemic Game for Civic Engagement" by Sherry Jone...Sherry Jones
1.7K views45 slides

Similar to Why AI Is Shaping our games - Johanna Pirker, 2019(20)

Artificial intelligence by sabairshad4
Artificial intelligenceArtificial intelligence
Artificial intelligence
sabairshad4150 views
2021 - We are Developers - How Data is Shaping our Games by Johanna Pirker
2021 - We are Developers - How Data is Shaping our Games2021 - We are Developers - How Data is Shaping our Games
2021 - We are Developers - How Data is Shaping our Games
Johanna Pirker70 views
9.5 Theses on the Power and Efficacy of Gamification by Sebastian Deterding
9.5 Theses on the Power and Efficacy of Gamification9.5 Theses on the Power and Efficacy of Gamification
9.5 Theses on the Power and Efficacy of Gamification
Sebastian Deterding3.7K views
Artificial Intelligence in Gaming by Anmol Sawhney
Artificial Intelligence in GamingArtificial Intelligence in Gaming
Artificial Intelligence in Gaming
Anmol Sawhney1.1K views
"The Perspective Game: An Epistemic Game for Civic Engagement" by Sherry Jone... by Sherry Jones
"The Perspective Game: An Epistemic Game for Civic Engagement" by Sherry Jone..."The Perspective Game: An Epistemic Game for Civic Engagement" by Sherry Jone...
"The Perspective Game: An Epistemic Game for Civic Engagement" by Sherry Jone...
Sherry Jones1.7K views
artificialintelligenceingaming-221113091057-b894cc20.pdf by ArghyaGayen2
artificialintelligenceingaming-221113091057-b894cc20.pdfartificialintelligenceingaming-221113091057-b894cc20.pdf
artificialintelligenceingaming-221113091057-b894cc20.pdf
ArghyaGayen24 views
Online gaming culture 2 by Anton367594
Online gaming culture 2Online gaming culture 2
Online gaming culture 2
Anton36759469 views
Game playing in artificial intelligent technique by syeda zoya mehdi
Game playing in artificial intelligent technique Game playing in artificial intelligent technique
Game playing in artificial intelligent technique
syeda zoya mehdi8.4K views
Artificial intelligence In Modern-Games. by Nitish Kavishetti
Artificial intelligence In Modern-Games. Artificial intelligence In Modern-Games.
Artificial intelligence In Modern-Games.
Nitish Kavishetti4.6K views
9,5 Theses on the Power and Efficacy of Gamification by Sebastian Deterding
9,5 Theses on the Power and Efficacy of Gamification9,5 Theses on the Power and Efficacy of Gamification
9,5 Theses on the Power and Efficacy of Gamification
Sebastian Deterding82.2K views
understanding our past to improve our future by Gillian Smith
understanding our past to improve our futureunderstanding our past to improve our future
understanding our past to improve our future
Gillian Smith411 views
Games and Crowds: Now, Near, Next by Ben Sawyer
Games and Crowds: Now, Near, NextGames and Crowds: Now, Near, Next
Games and Crowds: Now, Near, Next
Ben Sawyer652 views
AI and Interactive Narrative in 2019 by Mirjam Eladhari
AI and Interactive Narrative in 2019 AI and Interactive Narrative in 2019
AI and Interactive Narrative in 2019
Mirjam Eladhari184 views
Gameplaying in artificial intelligence by oceanparkk
Gameplaying in artificial intelligenceGameplaying in artificial intelligence
Gameplaying in artificial intelligence
oceanparkk1.3K views
Game Playing in Artificial Intelligence by lordmwesh
Game Playing in Artificial IntelligenceGame Playing in Artificial Intelligence
Game Playing in Artificial Intelligence
lordmwesh68.8K views

More from Johanna Pirker

Social Network Analysis of the Global Game Jam Network by
Social Network Analysis of the Global Game Jam NetworkSocial Network Analysis of the Global Game Jam Network
Social Network Analysis of the Global Game Jam NetworkJohanna Pirker
788 views35 slides
Motivational Active Learning - Reimagine Education 2015 by
Motivational Active Learning - Reimagine Education 2015 Motivational Active Learning - Reimagine Education 2015
Motivational Active Learning - Reimagine Education 2015 Johanna Pirker
819 views10 slides
Learning in Collaborative and Motivational Environments by
Learning in Collaborative and Motivational EnvironmentsLearning in Collaborative and Motivational Environments
Learning in Collaborative and Motivational EnvironmentsJohanna Pirker
9.3K views14 slides
ACM ITICSE 2014 - Talk on Motivational Active Learning by
ACM ITICSE 2014 - Talk on Motivational Active LearningACM ITICSE 2014 - Talk on Motivational Active Learning
ACM ITICSE 2014 - Talk on Motivational Active LearningJohanna Pirker
5.6K views27 slides
September Game Jam 2014 Graz by
September Game Jam 2014 GrazSeptember Game Jam 2014 Graz
September Game Jam 2014 GrazJohanna Pirker
7.2K views10 slides
Virtual Teal World by
Virtual Teal WorldVirtual Teal World
Virtual Teal WorldJohanna Pirker
3.3K views27 slides

More from Johanna Pirker(8)

Social Network Analysis of the Global Game Jam Network by Johanna Pirker
Social Network Analysis of the Global Game Jam NetworkSocial Network Analysis of the Global Game Jam Network
Social Network Analysis of the Global Game Jam Network
Johanna Pirker788 views
Motivational Active Learning - Reimagine Education 2015 by Johanna Pirker
Motivational Active Learning - Reimagine Education 2015 Motivational Active Learning - Reimagine Education 2015
Motivational Active Learning - Reimagine Education 2015
Johanna Pirker819 views
Learning in Collaborative and Motivational Environments by Johanna Pirker
Learning in Collaborative and Motivational EnvironmentsLearning in Collaborative and Motivational Environments
Learning in Collaborative and Motivational Environments
Johanna Pirker9.3K views
ACM ITICSE 2014 - Talk on Motivational Active Learning by Johanna Pirker
ACM ITICSE 2014 - Talk on Motivational Active LearningACM ITICSE 2014 - Talk on Motivational Active Learning
ACM ITICSE 2014 - Talk on Motivational Active Learning
Johanna Pirker5.6K views
September Game Jam 2014 Graz by Johanna Pirker
September Game Jam 2014 GrazSeptember Game Jam 2014 Graz
September Game Jam 2014 Graz
Johanna Pirker7.2K views
Design and Evaluation of a Learner-Centric Immersive Learning Environment for... by Johanna Pirker
Design and Evaluation of a Learner-Centric Immersive Learning Environment for...Design and Evaluation of a Learner-Centric Immersive Learning Environment for...
Design and Evaluation of a Learner-Centric Immersive Learning Environment for...
Johanna Pirker4.1K views
Learning in Virtual Worlds by Johanna Pirker
Learning in Virtual WorldsLearning in Virtual Worlds
Learning in Virtual Worlds
Johanna Pirker3.7K views

Recently uploaded

Renewal Projects in Seismic Construction by
Renewal Projects in Seismic ConstructionRenewal Projects in Seismic Construction
Renewal Projects in Seismic ConstructionEngineering & Seismic Construction
5 views8 slides
ASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdf by
ASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdfASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdf
ASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdfAlhamduKure
8 views11 slides
REACTJS.pdf by
REACTJS.pdfREACTJS.pdf
REACTJS.pdfArthyR3
37 views16 slides
MK__Cert.pdf by
MK__Cert.pdfMK__Cert.pdf
MK__Cert.pdfHassan Khan
19 views1 slide
sam_software_eng_cv.pdf by
sam_software_eng_cv.pdfsam_software_eng_cv.pdf
sam_software_eng_cv.pdfsammyigbinovia
10 views5 slides
2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx by
2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx
2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptxlwang78
180 views19 slides

Recently uploaded(20)

ASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdf by AlhamduKure
ASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdfASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdf
ASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdf
AlhamduKure8 views
REACTJS.pdf by ArthyR3
REACTJS.pdfREACTJS.pdf
REACTJS.pdf
ArthyR337 views
2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx by lwang78
2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx
2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx
lwang78180 views
Ansari: Practical experiences with an LLM-based Islamic Assistant by M Waleed Kadous
Ansari: Practical experiences with an LLM-based Islamic AssistantAnsari: Practical experiences with an LLM-based Islamic Assistant
Ansari: Practical experiences with an LLM-based Islamic Assistant
M Waleed Kadous9 views
MongoDB.pdf by ArthyR3
MongoDB.pdfMongoDB.pdf
MongoDB.pdf
ArthyR349 views
GDSC Mikroskil Members Onboarding 2023.pdf by gdscmikroskil
GDSC Mikroskil Members Onboarding 2023.pdfGDSC Mikroskil Members Onboarding 2023.pdf
GDSC Mikroskil Members Onboarding 2023.pdf
gdscmikroskil63 views
SUMIT SQL PROJECT SUPERSTORE 1.pptx by Sumit Jadhav
SUMIT SQL PROJECT SUPERSTORE 1.pptxSUMIT SQL PROJECT SUPERSTORE 1.pptx
SUMIT SQL PROJECT SUPERSTORE 1.pptx
Sumit Jadhav 22 views
Web Dev Session 1.pptx by VedVekhande
Web Dev Session 1.pptxWeb Dev Session 1.pptx
Web Dev Session 1.pptx
VedVekhande17 views
BCIC - Manufacturing Conclave - Technology-Driven Manufacturing for Growth by Innomantra
BCIC - Manufacturing Conclave -  Technology-Driven Manufacturing for GrowthBCIC - Manufacturing Conclave -  Technology-Driven Manufacturing for Growth
BCIC - Manufacturing Conclave - Technology-Driven Manufacturing for Growth
Innomantra 15 views
Design_Discover_Develop_Campaign.pptx by ShivanshSeth6
Design_Discover_Develop_Campaign.pptxDesign_Discover_Develop_Campaign.pptx
Design_Discover_Develop_Campaign.pptx
ShivanshSeth649 views

Why AI Is Shaping our games - Johanna Pirker, 2019

  • 1. S C I E N C E * PA S S I O N * T E C H N O L O G Y WHY AI IS SHAPING OUR GAMES D R . J O H A N N A P I R K E R , T U G R A Z , A U S T R I A L U D I C I O U S 2 0 1 9
  • 2. JOHANNA PIRKER ▸ Computer Scientist & Software Engineering @Graz University of Technology ▸ Virtual Realities (Maroon) @Massachusetts Institute of Technology ▸ Research & Edu at Institute for Interactive Systems & Data Science, @TUGraz ▸ Virtual Realities & Worlds ▸ HCI, E-Learning, UX, Data Analysis (SNA) ▸ Games Education (for CS) & 
 Research, Design, Development & Analysis ▸ GUR Consulting @BetterChaos ▸ Website: www.jpirker.com @JOEYPRINK
  • 5. “MAKING COMPUTERS ACT LIKE THEY DO IN THE MOVIES.”
  • 6. 1. THE CAPABILITY OF A MACHINE TO IMITATE INTELLIGENT HUMAN BEHAVIOR.
 2. A BRANCH OF COMPUTER SCIENCE DEALING WITH THE SIMULATION OF INTELLIGENT BEHAVIOR IN COMPUTERS. Merriam-Webster defines artificial intelligence this way.
  • 7. “REAL” AI ▸ 1. learn over time in response to changes in its environments ▸ (e.g. Netflix recommendations but not Twitter black lists) ▸ 2. what it learns should be interesting enough that it would take humans some effort to learn ▸ (Turing test)
  • 9. AI IN GAMES ▸ … generate responsive, adaptive, & intelligent behaviour ▸ uses path finding, decision trees, data mining, PCG, … ▸ usually do not facilitate computer learning ▸ -> predetermined & limited set of responses to a limited set of inputs ▸ ILLUSION OF INTELLIGENCE ▸ good gameplay without environment restrictions ▸ learn & use from “real AI” strategies ▸ Learning Tamagotchi
  • 10. ▸ decision trees (scripting) ▸ -> AI stupidity, predictive behaviour, loss of immersion ▸ pathfinding ▸ (Half Life, “Crouch Cover”) ▸ NPC behaviour in Doom ▸ NPCs fighting NPCs AI IN GAMES - ISSUES
  • 13. AI TO PLAY GAMES ROBOCUP
  • 14. AI TO PLAY GAMES CHESS - IBM DEEP BLUE VS. GARRY KASPAROV (1997)  "I could feel — I could smell — a new kind of intelligence across the table,"
  • 15. AI TO PLAY GAMES JEOPARDY! - IBM WATSON VS. KEN JENNINGS (2011)  "I could feel — I could smell — a new kind of intelligence across the table,"
  • 16. AI TO PLAY GAMES GO - GOOGLE ALPHAGO (DEEPMIND) VS. LEE SEDOL (2016)
  • 17. AI TO PLAY GAMES DEEPMIND VS. STARCRAFT II (2019)
  • 18. AI TO PLAY GAMES http://gameaibook.org/book.pdf
  • 19. ▸ Chess Two-player adversarial, deterministic, fully observable, branching factor ~35, ~70 turns ▸ Go Two-player adversarial, deterministic, fully observable, branching factor ~350, ~150 turns ▸ Frogger (Atari 2600) 1 player, deterministic, fully observable, bf 6, hundreds of ticks ▸ Halo 1.5 player, deterministic, partially observable, bf ???, tens of thousands of ticks ▸ Starcraft 2-4 players, stochastic, partially observable, bf > a million, tens of thousands of ticks ▸ Togelius AI TO PLAY GAMES
  • 20. AI TO PLAY GAMES TRAIN AI HOW TO PLAY SNAKE (DEEP REINFORCEMENT LEARNING) On the left, the agent was not trained and had no clues on what to do whatsoever. The game on the right refers to the game after 100 iterations (about 5 minutes). The highest score was 83 points, after 200 iterations. https://github.com/maurock/snake-ga
  • 21. AI TO PLAY GAMES TRAIN AI HOW TO PLAY STARCRAFT ‣ A Machine Learning API developed by Blizzard that gives researchers and developers hooks into the game. ‣ A dataset of half a million anonymised game replays,.   ‣ An open source version of DeepMind’s toolset, PySC2 ‣ A series of simple RL mini-games to test the performance of agents on specific tasks. https://deepmind.com/blog/deepmind-and-blizzard-open-starcraft-ii-ai-research-environment/
  • 22. AI TO PLAY GAMES WHY USE AI TO PLAY GAMES? ▸ Playing to win vs playing for experience ▸ For experience: human-like, fun, predictable…? ▸ Playing in the player role vs playing in a non-player role http://gameaibook.org/book.pdf
  • 23. METHODS ▸ Planning-Based ▸ Uninformed search (e.g. BFS),Informed search (e.g. A*), Evolutionary algorithms ▸ Reinforcement learning (training time) ▸ TD-learning / approximate dynamic programming, Evolutionary algorithms ▸ Supervised learning (requires play traces to learn from) ▸ Neural nets, k-nearest neighbors etc ▸ Random (requires nothing) AI TO PLAY GAMES ▸ Togelius
  • 28. CONTRIBUTE CONTENT PROCEDURAL CONTENT GENERATION • Artistic aspects • Corner-cases • Lack of complete control • Depends on the content • Client-side calculations? • Replayable content? • Cheap • Lots of content • Dynamic Reaction on player • Reduce burden of artist • Save memory • Large worlds • Replayable content • http://pcg.wikidot.com/category-pcg-algorithms
  • 29. METHODS ▸ Search-Based Methods ▸ Solver-Based Methods ▸ Grammar-Based Methods ▸ Cellular Automata ▸ Noise and Fractals ▸ Machine Learning CONTRIBUTE CONTENT
  • 30. GENERATE CONTENT FOR… ▸ Environments (Random Maps, Random Dungeons) ▸ Generative Art and models ▸ Textures ▸ Music ▸ Story ▸ Gameplay CONTRIBUTE CONTENT
  • 32. PLAYER MODELING PLAYER MODELING ▸ … detection, prediction and expression of human player characteristics that are manifested through cognitive, affective and behavioral patterns while playing games ▸ can be used to dynamically adjust the gameplay (dynamic difficult adjustment)
  • 34. B A R T L E ’ S G A M E R T Y P E S http://www.gamerdna.com/quizzes/bartle-test-of-gamer-psychology
  • 35. Story Story Enjoyer Party Player Killer Online Hero Allrounder 0% 20% 40% 60% 80% 100% Story Enjoyer Party Player Killer Online Hero Allrounder Time spent Story Campaign Arena Online MulAplayer Local MulAplayer P L AY E R H A B I T ( P L AY E R F I N G E R P R I N T )
  • 36. P L AY E R P R O F I L E S I N F O R Z A • What Drives People: Creating Engagement Profiles of Players from Game Log Data • 120 mio race entries from 1.2 mil players • Harpstead, E., Zimmermann, T., Nagapan, N., Guajardo, J. J., Cooper, R., Solberg, T., & Greenawalt, D. (2015, October). What Drives People: Creating Engagement Profiles of Players from Game Log Data. In Proceedings of the 2015 Annual Symposium on Computer-Human Interaction in Play (pp. 369-379). ACM.
  • 37. F L O W ( M I H A LY C S I K S Z E N T M I H A LY I )
  • 38. HOW PLAYSTYLES EVOLVE: PROGRESSION ANALYSIS AND PROFILING IN JUST CAUSE 2 https://link.springer.com/chapter/10.1007/978-3-319-46100-7_8
  • 39. F E AT U R E S • Spatio-temporal navigation • combat performance • progression through the main storyline • side quests.. • Agency missions (+ reach specific level of Chaos) • subset of features based on the core mechanics • -> does not impact the analytical framework • -> impacts the kinds of conclusions that can be derived
  • 40. P L AY E R P R O G R E S S I O N A L O N G T H E M I S S I O N S
  • 41. R E S U LT S • How can we describe player behaviour of the different player profiles?
  • 42. P L AY E R B E H AV I O U R A L O N G T H E S T O RY L I N E jpirker.com/jc2/aaSankey.html
  • 43. G O A L S • Improve our understanding of the different player behaviours and factors to improve engagement • Find issues to avoid drop-outs • Provide tools for game designers to (visually) analyse the game and improve the understanding of players • Find game design flaws early and automatically
  • 45. AI AS A PART OF GAME DESIGN!!!!
  • 46. AI TO DESIGN GAMES ROLES OF AI IN GAMES ▸ AI in the foreground of games - Foregrounding AI ▸ create gameplay based around thinking about how agents work ▸ Designing games that use AI techniques in a new way as a core of their gameplay https://medium.com/@mtrc/tombs-of-tomeria-7c2e800a6511 Mike Treanor, Alexander Zook, Mirjam P Eladhari, Julian Togelius, Gillian Smith, Michael Cook, Tommy Thompson, Brian Magerko, John Levine and Adam Smith: AI-Based Game Design Patterns. Computational Creativity and Games Workshop, 2015.
  • 47. AI-BASED GAME DESIGN ▸ Game design strategies/rules described when AI still “young” and most games are designed to not need AI ▸ Game designers often claim that AI won’t make games better ▸ Our goal: show where AI can be used, show alternative routes ▸ we need to design new games from scratch based on new design principles Mike Treanor, Alexander Zook, Mirjam P Eladhari, Julian Togelius, Gillian Smith, Michael Cook, Tommy Thompson, Brian Magerko, John Levine and Adam Smith: AI-Based Game Design Patterns. Computational Creativity and Games Workshop, 2015. AI TO DESIGN GAMES
  • 48. AI GAME DESIGN PATTERNS Mike Treanor, Alexander Zook, Mirjam P Eladhari, Julian Togelius, Gillian Smith, Michael Cook, Tommy Thompson, Brian Magerko, John Levine and Adam Smith: AI-Based Game Design Patterns. Computational Creativity and Games Workshop, 2015. AI TO DESIGN GAMES
  • 49. AI DESIGN PATTERNS 1 AI IS VISUALIZED ▸ Pattern: Provide a visual representation of the underlying AI state, making gameplay revolve around explicit manipulation of the AI state. ▸ Example: Third Eye Crime is a stealth game that illustrates this pattern by visualizing the guard AI position tracking and estimation system. Gameplay involves avoiding guards or throwing distractions to manipulate the guards’ predictions of player location. The direct visualization of AI state allows a designer to build a game around manipulating, understanding, and mentally modeling how the AI state changes.
  • 50. 2 AI AS ROLE-MODEL ▸ Pattern: Provide one or more AI agents for the player to behave similarly to. ▸ Example: Spy Party is a game where one player is a spy at a party populated by FSM agents and the opposing player is a sniper watching the party with a single shot to kill the spy. Gameplay for the spy centers on the player attempting to act similarly to the party agents while discreetly performing tasks in the environment like planting a bug or reading a code from a book. AI DESIGN PATTERNS
  • 51. 3 AI AS TRAINEE ▸ Pattern: Have player actions train an AI agent to perform tasks central to gameplay. ▸ Example: Black & White is a god game where the player trains a creature to act as an autonomous assistant in spatial regions where the player cannot take direct action. The creature learns sets of behaviors through a reward signal based on a needs model; the creature also takes direct feedback through player action (e.g., slapping or petting the creature after it takes actions). AI DESIGN PATTERNS
  • 52. 4 AI IS EDITABLE ▸ Pattern: Have the player directly change elements of an AI agent that is central to gameplay. ▸ Example: Galactic Arms Race is a space shooter where how the player uses different weapons evolves an underlying neural network representation to change weapon firing behavior. Base gameplay revolves around finding a set of firing behaviors that together enable a player to succeed at destroying opposition (another example of the AI as Trainee pattern). One gameplay mode allows the player to explicitly manipulate the network weights on weapons, allowing more precise control over the firing patterns of the evolved weapons. This control enables players to more finely explore the space of parameterizations, leading to an indirect way to understand the processes of the AI system. Erin J. Hastings, Ratan K. Guha, and Kenneth O. Stanley (2009) Automatic Content Generation in the Galactic Arms Race Video Game In: IEEE Transactions on Computational Intelligence and AI in Games, volume 1, number 4, pages 245-263, New York: IEEE Press, 2009. (Manuscript 19 pages) AI DESIGN PATTERNS
  • 53. 5 AI IS GUIDED ▸ Pattern: The player assists a simple or brittle AI agent that is threatened with self-destruction. ▸ Example: The Sims addressed the problem of “human-like” agents in a social world by making gameplay revolve around the player addressing the needs of simple agents. AI agents have a set of needs and desires they attempt to pursue while players intervene to provide for the needs of the agents through food, shelter, work, socialization, and eventually more grand life aspirations. By having players care for the AI, players come to (at least indirectly) model some of the processes used by the AI. AI DESIGN PATTERNS
  • 54. 8 AI AS VILLAIN ▸ Pattern: Require players to complete a task or overcome an AI opponent where the AI is aiming to create an experience (e.g., tension or excitement) rather than defeat the player. ▸ Example: Alien: Isolation is a first-person survival horror game where the opposing alien was designed to harass the player without using an optimal strategy that would always kill the player directly. The enemy alien spends the game hunting the player, displaying behaviors of seeking the player’s location (a weak version of AI is Visualized), and gradually learning from tactics the player uses repeatedly (an oppositional application of AI as Trainee). By having players continually reason on what the alien has learned and where it will go the player is forced to consider the state of the AI and (after repeated play) the processes involved in the AI learning. AI DESIGN PATTERNS
  • 58. AI TO DESIGN GAMES / COMPUTATIONAL CREATIVITY
  • 59. RESOURCES ▸ IEEE Computational Intelligence and Games (CIG) ▸ AAAI Artificial Intelligence in Interactive Digital Entertainment (AIIDE) ▸ Foundations of Digital Games (FDG) ▸ IEEE Transactions on Games (ToG) ▸ Yannakakis and Togelius: Artificial Intelligence and Games www.gameaibook.org
  • 60. THANK YOU FOR YOUR ATTENTION. JOHANNA PIRKER, JPIRKER@MIT.EDU, @JOEYPRINK 
 Further information: jpirker.com This is how others play your game!