5. Using AI in Computer Games (Decision making concepts)

NWC603COM – Using AI in Computer Games                                                        Rachel Osho                                                                                                                                              ID: 309740
Assignment 1 – Theory One

Decision making concepts

Decision trees

A decision tree is similar to a branching tree diagram transferring from node to node. Making decisions all the way from the top of the tree to the bottom. Decisions tree in regards to gaming helps artificial characters make a decision. Boolean responses (true or false/ yes or no) are used to represent responses within a decision tree. Decision trees are a concept that is near enough used within every game. The strengths of using decision trees is that the are easy to implement and is one of the most basic artificial techniques meaning that it’s simply an straightforward to learn and understand. Another benefit of decision trees is that they display fast execution. As we know the AI technique can be used in gaming to decide on how an AI character should respond to an enemy/ another AI character.

State machine

State machines is another descision making concept which is more advanced

can be easy to write initially and can be quite efficient. However state machines can also prove difficult to keep up with maintenance such as debugging

From the diagram above which is an example of a state machine we can see that the NPC (non player character) has a total of four different states that it can be in. These four different states are catorgoised under wander, attack, evade and find aid.

Firstly the NPC’s wanders round, however if another player is around then it will go into attack mode. If there is no other player then the NPC will result back to wandering. Then moving on to attack if the player begins to fight back then the NPC will evade. Should the player not fight back then the NPC will just stay in its attack state. Once the NPC evades and it’s health is low, then it is set to find aid to boost up its health points and lastly after finding aid the NPC will wander round. Then the state machine is set to rotate and continue in this cycle within the game.

Fuzzy Logic

First and foremost fuzzy logic officially became known about within the game development world 1996 Fuzzy logic is an essential artificial intelligence element that is required in great game. In addition to this fuzzy logic is literally used everywhere in technology ranging from dishwashers to electrical switches. (Pirovano, 2012) Fuzzy logic can also be used with a by other algorithms  or either artificial neural networks (ANN’s) which are classed as other artificial networks.

There are many advantages of fuzzy vlogic, one  that it is really useful in
regards to the AI aspect within a game.  Reason why it can be useful is that one of the purposes of fuzzy logic is that it can be used for a non-playable character decision making e.g. selecting  A weapon or items in the invorortrey as well as rating NPC’s in terms of power/health. Fuzzy logi can be seen to be very beneficial to AI game developer and should be simple for them to use since they are creating the fuzzy system these rules will be able to been so why any order making it simpler to either add or delete additional roles and a fuzzy system. In addition to this without fuzzy logic esssentiallh you are not able to do state machines. Another reason as to why fuzzy logic Is beneficial that the technique can be used to model complex behavioural with a low computational cost, which is often favoured by gamers. Fuzzy logics weaknesses occur when the rules are difficult to create causing a fair amount of tuning and then later leading to increased development time. (Pirovano, 2012 )Enemy nations, Sims the game and S.W.A.T 2 are all examples of game that use fuzzy logic.