210 likes | 231 Views
This project focuses on designing a real-time strategy game with a genetic AI, using a combination of heuristics and constants to optimize AI effectiveness. The AI is designed to produce quick heuristic algorithm combinations by eliminating suboptimal ones. Personality traits like aggressiveness and trustworthiness are integrated to make the AI more varied and humanlike, tracking opponent behavior for strategic advantage. Genetic algorithms are employed to evolve optimal strategies, facilitating autonomous optimization and decision-making. Game theory concepts such as war of attrition are explored, offering a model of human behavior. Lastly, the advantages and disadvantages of genetic algorithms are discussed along with Evolutionary Stable Strategies and Degree-Constrained Spanning Trees. The overall goal is to create an engaging and challenging gaming experience with intelligent AI opponents.
E N D
By Bharat Ponnaluri Design of a real time strategy game with a genetic AI
Abstract • Current strategy game AI • Involved combinations of heuristics and constants. • The combinations need to be optimized for the AI to be effective • Too many possible constants&combinations-->difficult optimization • Chess heuristic evaluations • Moves available • Is the king safe • Pawn structure • Material balance • Genetic AI • Can produce constants and combinations of heuristic algorithms quickly by eliminating suboptimal combinations.
Introduction • Design of a simple real time strategy game • Build troops and try to take over cities • Like Risk in real time • Goal is to have an intelligent AI optimized with genetic algorithms • AI design • Coding of simple building block heuristic evaluation functions • Addition of constants(Agressiveness,stinginess) that determine behaviour • Chromosomes will be random combinations of • Heuristic evalution functions • Used to evaluate the quality of a possible course of action based on game data
Personality Traits • Goal: To make the AI more interesting and humanlike • Traits • Agressiveness • Paranoia • Stinginess • Vengence • Trustworthiness
Observation • AI will take advantage of other players' behavior • Examples • Assertivness • The AI will keep track of when a player retreats • The AI will attack a player which retreats a lot • Attacking game leader • One player is threatening to win • AI will track who tries to stop that player • Then the AI will let that player do the work
Game Theory • Advantages • Not very complicated • Easily understandable by AI • Good model of human behavior
Game Theory: War of attrition • Two players fighting over city • Backing down=loss in percieved assertiveness • Fighting=massive loss in strength • t=time that conflict lasts
Sample chromosome • Chromosome • enemyStrength()/2*myStrength()-3*fooA()/43.........+power() • Possible genes • public int fooA() • .... • public int enemyStrength() • .... • public int myStrength()
Heuristic evaluation functions • Heuristic evaluation functions • Used to evaluate the quality of a possible course of action based on game data • Example: • Public int getTrafficJamFactor() • Return ( 1.001^(number of cars))/roadSize
Game Theory • Advantages • Easy to understand • Representes humanlike behavior • Simple for computer to follow
How do genetic algorithms work • Replicate evolution • Steps • Determine random combinations of heuristics and constants(chromosomes) • Test chromosomes • Remove suboptimal chromosomes • Mutate surviving chromosomes • Swap data between surviving chromosomes • If chromosomes are optimal,end algorithm • Otherwise, repeat steps 1-7
Advantages and Disadvantages • Advantages • Can function without user input • Can optimize a large number of constants • Usually is very good at optimizing stuff • Can determine unknown solutions • Possible disadvantages • Genetic algorithms are complicated • Take a significant amount of computing power • Networking will increase complexity
Evolutionary Stable Strategies(ESS) • Gene pool of defectors means cooperating players will lose • Advantages • Diverse AI personalities • Disadvantages • May lead to suboptimal/boring AI's
ESS: Example • Population of turtling AI's • AI's only counterattack or attack weak players • A more balanced AI will lose • Playing against a group of turtling AI's is boring
Degree-Constrained Spanning Trees • Degree constrained spanning tree • All verticies are nodes • Maximum number of leaves per node • Genetic algorithm • Optimized weights for a heuristic evaluation function
Tiddlywinks • Fit largest possible circle that does not overlap discs • Genetic algorithm • Generates random circles • Keeps the larger circles
Generating a target number using a mathematical expression • Combination of numbers(1-9) and mathematical operators(-,+,*,/) adding up to a target number • Each number=4 bits • Chromosome • 0110 1010 0101 1100 0100 1101 0010 1010 0001 • 6+5*4/2 +1 • Suboptimal chromosomes-->result far from target number • Can be scaled for large numbers &decimals • No attempting to use brute force to test out random combinations.
New Heurstics • Find Targets() • Average proximity • Income power factor • Troop power factor • Potential borders
Testing results • Numbers greater than 1 are not good • From last working version(before new heurstics)
Conclusion • Speed is an issue • Debugging was unexpectedly difficult