Presentation is loading. Please wait.

Presentation is loading. Please wait.

AI and GAMES CSC 8520, Villanova University Spring, 2004 Paula Matuszek & Robin McEntire.

Similar presentations


Presentation on theme: "AI and GAMES CSC 8520, Villanova University Spring, 2004 Paula Matuszek & Robin McEntire."— Presentation transcript:

1 AI and GAMES CSC 8520, Villanova University Spring, 2004 Paula Matuszek & Robin McEntire

2 Some games to explore Yahoo AI Games directory. Mostly chatbots; 20 questions is good. Yahoo AI Games directory. Mostly chatbots; 20 questions is good. Yahoo AI Games directory 20 questions Yahoo AI Games directory 20 questions Yahoo Artificial Life. I like Insaniquarium. Yahoo Artificial Life. I like Insaniquarium. Yahoo Artificial Life Insaniquarium Yahoo Artificial Life Insaniquarium Chinook. The world man-machine champion checkers player. Chinook. The world man-machine champion checkers player. Chinook. A Mastermind variant. A Mastermind variant. A Mastermind variant A Mastermind variant Othello (Reversi). One of the classic neural net testbeds. Othello (Reversi). One of the classic neural net testbeds. Othello (Reversi) Othello (Reversi) Battleship (Armada). Battleship (Armada). Battleship (Armada). Battleship (Armada). The entire Yahoo web games directory can be fun to explore. Which of these seem to have an AI component? The entire Yahoo web games directory can be fun to explore. Which of these seem to have an AI component?Yahoo web games directoryYahoo web games directory

3 GAMES and AI Most of these games are using AI. Here are some discussion points: Most of these games are using AI. Here are some discussion points: Agents: which of these games have autonomous agents? What’s the PEAS description? Agents: which of these games have autonomous agents? What’s the PEAS description? What AI techniques are being used? What AI techniques are being used? –A* search (eg, for path finding) –Alpha-Beta search (eg, for choosing a move) –Knowledge representation –Natural language processing –Artificial life and flocking/swarming –Reasoning –Learning

4 Insaniquarium Agents with PEAS? Agents with PEAS? –Performance measure –Environment –Actuators –Sensors Search? Search? Knowledge Representation? Knowledge Representation? Natural Language processing? Natural Language processing? Logic and inference? Logic and inference? Other? Other?

5 Chinook Agents with PEAS? Agents with PEAS? –Performance measure –Environment –Actuators –Sensors Search? Search? Knowledge Representation? Knowledge Representation? Natural Language processing? Natural Language processing? Logic and inference? Logic and inference? Other? Other?

6 Battleship Agents with PEAS? Agents with PEAS? –Performance measure –Environment –Actuators –Sensors Search? Search? Knowledge Representation? Knowledge Representation? Natural Language processing? Natural Language processing? Logic and inference? Logic and inference? Other? Other?

7 Mastermind Agents with PEAS? Agents with PEAS? –Performance measure –Environment –Actuators –Sensors Search? Search? Knowledge Representation? Knowledge Representation? Natural Language processing? Natural Language processing? Logic and inference? Logic and inference? Other? Other?

8 Role Playing Games: Non-Player Characters (Helpers, Opponents) Agents with PEAS? Agents with PEAS? –Performance measure –Environment –Actuators –Sensors Search? Search? Knowledge Representation? Knowledge Representation? Natural Language processing? Natural Language processing? Logic and inference? Logic and inference? Other? Other?

9 Summary Even very basic AI can contribute to games in a variety of ways. Even very basic AI can contribute to games in a variety of ways. Most important single AI technique for gaming? Probably A*. Most important single AI technique for gaming? Probably A*. AI can provide opponents, partners, support characters, story directors, commentators. AI can provide opponents, partners, support characters, story directors, commentators. AI and artificial life are fun. ALife doesn’t have to be Turing-test level of intelligence for good gaming. AI and artificial life are fun. ALife doesn’t have to be Turing-test level of intelligence for good gaming.

10 From a GAME perspective There are two fields that are relevant here AI: AI: –AI has techniques to contribute to games. –Games are a fertile field for AI research. Games: Games: –Gaming has enormous market importance. –Games are growing increasingly sophisticated in all dimensions –A game has to be fun; use whatever AI techniques aid that.

11 Game Design, Game AI Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

12 Background: Game Genres Racing – other cars Racing – other cars Action – enemies, allies Action – enemies, allies Real Time Strategy (RTS) –units, commanders (for both sides) Real Time Strategy (RTS) –units, commanders (for both sides) Role Playing Games (RPG) – monsters, party members, Non Player Characters Role Playing Games (RPG) – monsters, party members, Non Player Characters Sports – players, coaches, commentators Sports – players, coaches, commentators Shooter – targets, more targets Shooter – targets, more targets Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

13 Obvious Examples of AI Car Game – write a virtual driver Car Game – write a virtual driver Shooter – write a virtual player Shooter – write a virtual player Sports Games – write a virtual coach Sports Games – write a virtual coach RTS – write a virtual general RTS – write a virtual general Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

14 Mini Case Study: Racing Game History No “AI” cars, only real players are drivers No “AI” cars, only real players are drivers “AI” cars which follow scripted path “AI” cars which follow scripted path Follow path, adjust speed Follow path, adjust speed Feedback system to follow path Feedback system to follow path “Rubber band” near player “Rubber band” near player Attempt to have driver “personality” Attempt to have driver “personality” Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

15 Somewhat Real Examples Car Game – write AI to keep races close Car Game – write AI to keep races close Shooter – enemies die lots, win little Shooter – enemies die lots, win little Sports – commentators, help player Sports – commentators, help player RTS – generals who work on pacing RTS – generals who work on pacing It is A Question of Design Purpose It is A Question of Design Purpose Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

16 Game Development What is the goal for Player Experience? What is the goal for Player Experience? How is the AI going to further that goal? How is the AI going to further that goal? Role of the designer Role of the designer Role of the programmer Role of the programmer How “design” evolves How “design” evolves Constraints Constraints Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

17 Roles of a Game AI Tool for the designer Tool for the designer Foil for the player, creates opportunity Foil for the player, creates opportunity Dynamic challenge Dynamic challenge Events: Emulation v. Simulation Events: Emulation v. Simulation Assists in Driving the action Assists in Driving the action Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

18 Shipping Games vs. Test Code Hard constraint on CPU usage Hard constraint on CPU usage Reproducibility is vital, for test and design Reproducibility is vital, for test and design Must be fun, not correct Must be fun, not correct Must succeed, finish, do something, always Must succeed, finish, do something, always Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

19 Mini Case Study The Thief AI Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

20 Design Goals Player is going to be a Thief Player is going to be a Thief i.e. Sneak Around, Ambush, Hide, Steal i.e. Sneak Around, Ambush, Hide, Steal –AI must allow players to make plans –And react to player actions, provide challenge Game will feature a loose overall story Game will feature a loose overall story –Ability to script/override behavior –In-game actions fed back out to story control Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

21 “Watch-able” by the player Has to “go about it’s business” with intent Has to “go about it’s business” with intent Actions must make sense to player Actions must make sense to player –“interestingly predictable” –present play opportunities for player Overemphasize thoughts Overemphasize thoughts –Telegraph all actions –Goals must be very explicit Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

22 Implementation Model senses, detection, awareness Model senses, detection, awareness Simple event based “reaction” scripts Simple event based “reaction” scripts Tagging of world objects which notify AI Tagging of world objects which notify AI Patrol paths, dynamic “go-to-object” Patrol paths, dynamic “go-to-object” Rule based match database for speech Rule based match database for speech Heavily designer driven, toolset approach Heavily designer driven, toolset approach Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

23 Requirements Focus on the Player Experience Focus on the Player Experience Allow player to understand AI actions Allow player to understand AI actions Needs to achieve design aim (and fun) Needs to achieve design aim (and fun) Configurable, Override-able, Testable Configurable, Override-able, Testable Satisfies data and speed constraints Satisfies data and speed constraints Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt

24 Themes Player Player Player Player Player Player Player Player Player Player Player Player How can AI enhance player experience How can AI enhance player experience AI is facilitator of the “fun” AI is facilitator of the “fun” Enable creative expression for player Enable creative expression for player –Allow player to impact the world –Put player in interesting situations Based on: Doug Church, October, 2001: ai.eecs.umich.edu/people/laird/game-seminar/Doug-Church.ppt


Download ppt "AI and GAMES CSC 8520, Villanova University Spring, 2004 Paula Matuszek & Robin McEntire."

Similar presentations


Ads by Google