So, I want to implement AI to my LibGDX 2d platformer game. I have read stuff about A* pathfinding, but I think that if I make an A* pathfinding the performance would be very bad(on android), it is not great already. Then I stumbled upon an article w
I am currently developing a turn-based grid-based strategy game (similar to Heroes of Might and Magic and Age of Wonders) using C#. Focusing on the combat part first. There are multiple units on a grid, taking turns on attacking, shooting, casting sp
I'm learning how add the max-min ant system into my current ant system. From what I've read the trial pheromone is initialized tMax, tMax is calculated by, tMax = 1 / best tour length But how exactly would it be possible to initialize the trail phero
I have the Jaime model in jmonkey navigating to a specified point. This works great, what I can't get to work, is that once he arrives I want him to turn around and go back to the origin. I basically want the model to travel on a patrolling loop unti
I am trying to design a Chess Game that will work based on the fuzzy logic. Before making a move, I wanted to compute a fuzzy evaluation function for each chess piece in each play. The fuzzy computations are based on the data that are provided in the
I could not understand how to update Q values for tic tac toe game. I read all about that but I could not imagine how to do this. I read that Q value is updated end of the game, but I haven't understand that if there is Q value for each action ? ----
I'm trying to put Transposition tables into my alpha beta scout. I do see an incremental speed boost I think toward mid or late game, however, even with a table size of 1-2GB, its may or may not be slower than just not reading from the Transpose tabl
This question arose in my mind while I was trying to pass the open MIT 6.034 course dedicated to AI field. It seems to me, that Python is much more preferrable, than most of other popular languages. The different collections of courses for AI study a
What exactly is the difference between growing a NN and using a cascade NN, or is this the same thing? What I get from various sources, is that growing simply adds additional neurons and initializes its weights randomly. Adding new neurons is stopped
I've been looking into ways I can implement an adaptive mutation rate for a genetic algorithm I'm working on. I've seen an algorithm which uses the current individuals fitness and the average population fitness to calculate a mutation rate, however I
It seems there is a bit of confusion between activation and transfer function. From Wikipedia ANN: It seems that the transfer function calculates the net while the activation function the output of the neuron. But on Matlab documentation of an activa
I think this should be an AI problem. Is there any algorithm that, given any number sequence, can find patterns? And the patterns could be abstract as it can be... For example: 12112111211112 ... ( increasing number of 1's separated by 2 ) 1022033304
The aim is to guide a bot from Source S to Goal G while passing through all the checkpoints @ (in any order). The cells marked as # cannot be accessed. The bot can move on locations marked . ######## #@....G# ##.##@## #[email protected]# #@.....# ######## One w
I'm trying to implement an A star searching method for a college work, so i kinda need to make it from scratch, but I'm having some trouble making it work the correct way. Here's a picture of my problem: As you can see, it does find a path, but not t
Today in class, my professor introduced us to admissable heuristics and stated that they guarantee optimality for the A* algorithm. I asked him to explain it using an extreme example to make it obvious but he couldnt. Can someone please help? -------
I'm trying to implement an AI for a game of 'continuous snake'. It's very different from a normal snake game, at least as far as the AI is concerned. Basically, the snake drives a bit like a car and the first one of the 2 players to crash into his tr
I know the theorical difference between theses methods, but someone could give an example that make SVM != MPM? I think it's the same thing. An image would be awesome. SVM: Maximize margin between 2 samples classes MPM: Minimize the probability of wr
I am reading the book -- Artificial Intelligence a modern approach. I came across this sentence describing the time complexity of uniform cost search Uniform-cost search is guided by path costs rather than depths, so its complexity is not easily char
Hi I want to implement a small code I am not able to understand from where to start. I want to create a text field if user enter some text into text field I want to detect category of this text. For example if user enter "How to create an app for iOs
I recently asked the following question about the error requires numeric/complex matrix/vector arguments when working with the neuralnet library. Here is my original question: "Working with neuralnet in R for the first time: get "requires numeric/com