This presentation explores the important role of Artificial Intelligence in existing and future games.

1. AI IN GAMING
Anmol Sawhney
Jaysheel Shah
Pranav Shrivastava
1

2. INTRODUCTION
• According to the father of Artificial Intelligence, John McCarthy, it is “The
science and engineering of making intelligent machines, especially intelligent
computer programs”.
• Basically, Artificial Intelligence is a way of making a computer, a computer-
controlled robot, or a software think intelligently, in the similar manner the
intelligent humans think.
• Applications of AI -
a) Gaming − AI plays crucial role in strategic games such as chess, poker, tic-tac-
toe, etc., where machine can think of large number of possible positions based
on heuristic knowledge.
b) Natural Language Processing
c) Expert Systems
d) Vision Systems
e) Speech Recognition
f) Handwriting Recognition
g) Intelligent Robots
2

3. • Artificial intelligence has long been an important part of game development
practices. The forces of change in the industry present an opportunity for Game
AI to have new and profound impact on game production practices.
• A number of changes are occurring in the field of computer game development:
persistent online games, digital distribution platforms and portals, social and
mobile games, and the emergence of new business models have pushed game
development to put heavier emphasis on the live operation of games.
• The possibilities opened up by applying science to videogames are vast: the
integration of feelings in artificial players and the option to build a direct channel
between them and the sentimental perception of the player through the so-called
Affective Computing.
• Games provide a useful window into the increasing sophistication of AI.
Developers such as Google’s DeepMind and Elon Musk’s OpenAI have been
using games to teach AI systems how to learn.
• So far, these systems have bested the world’s greatest players of the ancient
strategy game Go, and even more complex games like Super Smash Bros
and DOTA 2.
3

4. MOTIVATION
• Learning artificial intelligence field can help one to perform complex
tasks that are otherwise difficult to perform.
• We can train our computer to predict and perceive next course of action
and know before hand the outcome of your research.
• Today, we are witnessing a growing fusion of VFX (Visual Effects)
industry and gaming, which suggests that people outside the industry
become aware of gaming as a powerful playground for innovation.
• AI techniques will include features like real-time interrogation of
suspects, dynamic movement, and richness of behaviour in game design
which increase the interaction between creatures and their environment,
giving a better experience.
4

5. THE EVOLUTION OF GAMING AI:
NON PLAYER CHARACTERS(NPC’S)
Examples of NPCs. Clockwise from top left: An
Ork from Space Marine, an interview subject from
L.A. Noire, a guard from Sky rim, and two
soldiers from Bio shock Infinite.
• Game AI is mainly associated with
the development of behaviors in
non-player characters (NPC’s)
although not exclusively personified.
• It’s mainly used to imitate
humanlike characteristics, enhance
gameplay and improve user
experience.
• Non-Player Characters (NPCs), or
NPCs, are characters within a
computer game that are controlled
by the computer, rather than the
player.
5

6. • NPC behavior in computer games is usually scripted and
automatic, triggered by certain actions or dialogue with the
player characters. More complex games allow the player to
customize the NPCs' behavior by modifying their default
scripts or creating entirely new ones.
• In early and less advanced RPGs, NPCs only had monologue.
Code directs the appearance of a dialogue box, floating text or
other means of displaying the NPCs' speech or reaction to the
player. NPC speeches of this kind may also advance the story.
• In recent times, system is hooked in to Microsoft's cloud
services, where it can pull in AI NPCs based on other human
players as well as crunch greater amounts of data from each
player. Now your AI opponents mimic other players from
around the globe their silly mistakes, quirks, strengths, and
weaknesses which makes for a more unpredictable experience.
• In some online games, NPCs may be entirely unscripted, and
are essentially regular character avatars controlled by
employees of the game company. In other cases, these "live"
NPCs are virtual actors, playing regular characters which drive
a continuing storyline.
6

7. ARTIFICIAL INTELLIGENCE AS
DESIGNER
• One of the roles of Game AI is to mediate between the human
designer/developer and the human-computer system comprised
of game and player. Game designers are responsible for building
and defining a game, analyzing how players interact with the
game, and iteratively refining a game to achieve a design vision.
• This paradigm for artificial intelligence is often referred to as
Procedural Content Generation (PCG) algorithms and
representations for generating any and all components of games.
Offline content generation emphasizes producing content
designers may curate or refine as a means of increasing the
efficiency of the game development process.
• Online, or just-in-time, generation focuses on providing larger
amounts of variation than human designers can achieve alone
and/or tailoring content to a given user. A primary concern for
PCG researchers has been ways to appropriately represent game
content to suit generation algorithms.
7

8. • Game adaptation combines content generation and player modeling to enable AI
designers to tailor games to individual players, emphasizing a closed loop of
modeling player actions and automated adjustment of game content based on
design goals for player behavior, player skill acquisition, or maximizing player
enjoyment.
• The availability of large data sets is having an impact on those who see AI as
designer. In particular, game analytics involves capturing, aggregating,
understanding, and visualizing player behavior to support designer understanding.
8

9. AI ALGORITHMS USED IN GAMING
• Decision trees are evaluated from root to leaf,
every time. For a decision tree to work properly,
the child nodes of each parent must represent all
possible decisions for that node. If a node can be
answered "Yes, No, Maybe", there must be three
children. The traversal is always down.
• “Black and White” was an extraordinary game that
pushed the envelope when it came to artificial
intelligence in entertainment. Creatures from the
game were the most realistic representations of
living, learning things to ever come out of the
gaming industry.
• After a creature completes an action to satisfy a
certain desire it will look at how well that desire
was satisfied and adjust its internal weight
structure accordingly . For example, a creature has
to act in a particular way when facing new
creatures in the game. Through feedback table it
will build this decision tree.
9

10. BREADTH FIRST SEARCH
• It starts from the root node, explores the
neighboring nodes first and moves towards the next
level neighbors. It generates one tree at a time until
the solution is found. It can be implemented using
FIFO queue data structure. This method provides
shortest path to the solution.
• If branching factor (average number of child nodes
for a given node) = b and depth = d, then number of
nodes at level d = bd.
• The total no of nodes created in worst case is b +
b2 + b3 + … + bd.
• Since each level of nodes is saved for creating next
one, it consumes a lot of memory space. Space
requirement to store nodes is exponential.
• Its complexity depends on the number of nodes. It
can check duplicate nodes if needed.
10

11. A* SEARCH ALGORITHM
• Consider a square grid having many obstacles
and we are given a starting cell and a target
cell. We want to reach the target cell (if
possible) from the starting cell as quickly as
possible.
• At each step it picks the node according to a
value-‘f’ which is a parameter equal to the sum
of two other parameters – ‘g’ and ‘h’. At each
step it picks the node/cell having the lowest ‘f’,
and process that node/cell.
a) g = the movement cost to move from the
starting point to a given square on the grid,
following the path generated to get there.
b) h = the estimated movement cost to move
from that given square on the grid to the final
destination. This is often referred to as the
heuristic.
c) F(n) = g(n)+h(n), here n is the last node in the
path.
11

12. INFERENCES
• Gaming AI will hold a major role in future. Since we human beings
are so fascinated by the different advancements in the field of
gaming, we don’t realize how manipulative these games could be.
• Even though realize that NPCs are just a figment of the designers
imagination, they can still affect users in various ways.
• Game developers have long sought to have meaningful and
logical interactions between human players and NPCs.
Unfortunately, except for restricted circumstances, typically
violent confrontations, this has not materialized successfully,
leaving the players feeling isolated or disconnected from the
world in which they are playing.
12

13. CONTINUED
• A key element to overcoming this problem is the
development of artificial intelligence capable of
dynamically reacting to players and player actions in
reasonable and realistic fashions. Doing so would require
a sense of relationship or social network binding the
characters and objects in the game world to one another.
• This is necessary as without the adaptability of AI,
programmers have to rely on scripted methods
implementing character behavior, mimicking character
reactions, which is very limiting .
13

14. CONCLUSION
• Artificial Intelligence has come as a revolution in the gaming industry.
We have heard about its application in the real world, however it has
come a long way in giving users a very realistic experience while
gaming.
• The use of NPCs has changed entirely from being just characters reading
lines to actual depictions of human emotions. This helps make the NPCs
unpredictable, which in turn makes the game an experience for the user.
• Searching algorithms are necessary for proper implementation of AI in
gaming. The decision each NPC makes depends on the information it is
provided. This process needs to be fast and efficient. Hence, the need for
searching algorithms.
• Game AI is integral in mediating between the user and the game. Game
designers must always be very careful as to what algorithms to use and
must have an established design vision prior to any coding or designing.
14

15. REFERENCES
• “Artificial Intelligence and its Application in Different Areas, International Journal of Engineering and Innovative
Technology (IJEIT) Volume 4, Issue 10, ”-Avneet Pannu, M. Tech Student, Department of Computer Science &
Engineering, DAV Institute of Engineering and Technology, Jalandhar,India.
• “Game Artificial Intelligence: Challenges for the Scientific Community”
• Authors:Raúl Lara-Cabrera, Mariela Nogueira-Collazo, Carlos Cotta and Antonio J. Fernández-Leiva.
• Leif Gruenwoldt, Michael Katchabaw Stephen Danton Department of Computer Science Horseplay Studios The
University of Western Ontario Seattle, Washington, USA London, Ontario
• http://hmi.ewi.utwente.nl/verslagen/capita-selecta/RT-Oude-Veldhuis-Mark.pdf
• https://www.cc.gatech.edu/~riedl/pubs/cig13.pdf
• Artificial Intelligence in Games: A look at the smarts behind Lion head Studio’s “Black and White” and where it can and
will go in the future James Wexler University of Rochester, NY.
• Ashwin Ram, Santiago Ontanon, and Manish Mehta ´ Cognitive Computing Lab (CCL)
College of Computing, Georgia Institute of Technology Atlanta, Georgia, USA
• Research Directions for AI in Computer Games. Chris Fairclough, Michael Fagan, Brian
Mac Namee, Pádraig Cunningham Department of Computer Science, Trinity College, Dublin
2, Ireland.
• http://www.streetdirectory.com/travel_guide/141271/gaming/the_benefits_of_artificial_intelli
gence_in_computer_games.html
• Expressive AI: Games and Artificial Intelligence Michael Mateas The Georgia Institute of
Technology School of Literature, Communication & Culture and College of Computing 686
Cherry Street Atlanta, GA 30332-0165 USA +1 404 894 2739 michaelm@cc.gatech.edu
• https://gamedev.stackexchange.com/questions/10876/adaptive-ai-artifical-intelligence
15

16. THANK YOU
16