Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [genetic-algorithms]

A method for solving constrained and unconstrained optimization problems based on natural selection processes. Use this tag for questions about GA; programming questions are off-topic. See https://ai.meta.stackexchange.com/q/71/1671

2
votes
1answer
55 views

What kind of algorithm can invent?

Set aside networks, image classification, gradients, and the strength of intelligence for a moment and consider the world before people lit fires. Fires were started periodically just as they are now,...
2
votes
3answers
56 views

Do genetic algorithm and neural networks really think?

I'm aware of those AI programmes which can play games and neural networks which can identify pictures. But are they really thinking. Do they think like humans? Do they have consciousness? Or are they ...
1
vote
0answers
18 views

How to use Genetic Algorithm for varying lengths of solutions

Until now, I always thought that Genetic Algorithm can be used for problems of which the solution space can be encoded (modeled) as a chromosome of a specific length. However, some people claim that ...
0
votes
0answers
14 views

Genetic Algorithm has too much fluctuation concerning fitness

I am using a NEAT-Algorithm where an ANN-population shall learn a game. The inputs are 9 and the outputs 2. So it should definitely work without a GPU-Cluster... The problem is, that there are ...
6
votes
4answers
133 views

Spontaneous emergence of replicators in Artificial Life

One of the corner stones of The Selfish Gene (Dawkins) is the spontaneous emergence of replicators, i.e. molecules capable of replicating themselves. Has this been modeled in silico in open-ended ...
1
vote
1answer
39 views

Fitness function in genetic algorithm based on an interval

I am writing an app, where when a ball is shot from a canon it is supposed to land in a hole which is on a given distance. The ball is supposed to land between the distance of the begining of the hole ...
1
vote
1answer
24 views

Representation of real numbers in Genetic Algorithm

Take a look at section 2.2.2 of this book (from Page-15 to 16). 2.2.2 Representation and Evaluation $$max f (x)= x sin(10πx)+2.0 ... ... ... (2.8)$$ $$s.t. −1 ≤ x ≤ 2$$ We can use a ...
1
vote
2answers
52 views

Learning Genetic algorithm for beginners

What is the best and easiest programming language to learn to implement Genetic algorithms? C++ or Python or any other?
1
vote
0answers
41 views

NEAT + Keras : reproducibility problem (World Models implementation)

I'm trying to apply the World Models architecture to the Sonic game (using the gym-retro library). My problem concerns the evolutionnary algorithm part that I use as the controller (worldmodels = ...
1
vote
1answer
52 views

How to optimize a function using a genetic algorithm?

I recently learned about Genetic algorithms and I solved the 8 queens problem using a genetic algorithm but I don't know how to optimize any functions using a genetic algorithm. I want a guide on how ...
1
vote
3answers
58 views

Can genetic algorithms be used to learn to play multiple games of the same type?

Is it possible for a genetic algorithm + Neural Network that is used to learn to play one game such as a platform game able to be applied to another different game of the same genre. So for example, ...
3
votes
1answer
38 views

Genetic Algorithms: Trade-off between time and variance with regards to fitness function

I'm developing an AI to play a card game with a genetic algorithm. Initially, I will evaluate it against a player that plays randomly, so there will naturally be a lot of variance in the results. I ...
1
vote
1answer
34 views

A3C & TWEAN (NEAT)

As a amateur researcher and tinkerer, I've been reading up on neuro-evolution networks (e.g. NEAT) as well as the A3C RL approach presented by Mnih et al and got to wondering if anyone has ...
1
vote
1answer
31 views

How can I calculate MBF in genetic algorithms?

I've just started to learn genetics algorithms and I have found these measurements of runs that I don't understand: MBF: The mean best fitness measure (MBF) is the average of the best fitness ...
1
vote
0answers
55 views

Genetic Algorithm to Play Arkanoid(Nes) Possible Crossover and Fitness?

I am using the Fceux emulator to create a Genetic Algorithm in Lua to play the 'Arkanoid' game. It is based on Atari Breakout. A member of my population contains a string of 0's and 1's.(Population ...
3
votes
1answer
190 views

Genetic Algorithm - creatures in 2d world are not learning

Goal - I am trying to implement a genetic algorithm to optimise the fitness of a species of creatures in a simulated two-dimensional world. The world contains edible foods, placed at random, and a ...
1
vote
1answer
72 views

NEAT - how to restrict neural network structure to be acyclic?

I want my neural network structure to not have a circular/looping structure something similar like a directed acyclic graph(DAG), how do I implement a restriction for that?
1
vote
1answer
178 views

NEAT crossover - what to do with disjoint and excess genes

According to the original paper "Genes that do not match are inherited from the more fit parent" But what if the more fit parent has lesser nodes compared to the other, will the disjoint/excess genes ...
1
vote
4answers
222 views

Can AI be programmed to not to lie?

We know that AI can lie. But, can evolutionary (self-learning) AI be programmed in such a way that they don't lie, even as they evolve? SOURCE: Evolving Robots Learn To Lie To Each Other (Popsci) ...
1
vote
1answer
193 views

How to evaluate a NEAT neural network?

I'm trying to write my own implementation of NEAT and I'm stuck on the network evaluate function, which calculates the output of the network. NEAT as you may know contains a group of neural networks ...
4
votes
1answer
46 views

Summed weights are too big for activation function [GANN]

I am trying to create a fixed-topology MLP network from scratch (C#) which can classify some simple problems such as XOR and MNIST (Handwriting). The network will be trained purely with genetic ...
3
votes
1answer
366 views

Implementing the “original” NEAT algorithm in JavaScript

I've recently read the original paper about NeuroEvolution of Augmenting Topologies by Kenneth O. Stanley and am now trying to prototype it myself in JavaScript. I stumbled across a few questions I ...
2
votes
2answers
177 views

What's the difference in between biological evolution and artificial evolution?

I am trying to understand the difference between the workings biological evolution and artificial evolution. If we look at it in terms of genetics, in both of them, selection is the key term, natural ...
1
vote
1answer
101 views

NEAT - Can mutation enable a disabled connection?

In the add node mutation, the connection between two chosen nodes (e.g A and B) is first disabled and then a new node is created between A and B with their respective two connections. I guess that the ...
4
votes
2answers
174 views

NEAT - Innovation for Connection genes only?

Does NEAT requires only connection genes to be marked with a global innovation number? From the NEAT paper Whenever a new gene appears (through structural mutation), a global innovation number is ...
1
vote
1answer
40 views

Which algorithm for scheduling race grid?

I want to plot a schedule of races based on rules. Rules like "each team needs at least 2 races between their next race" and some teams (e.g. collegiate) need to be clumped near each other. What ...
0
votes
0answers
103 views

Number of hidden layers/neurons for Connect4 Neural Networks

I have developed a neural network program to evolve neural nets to play connect 4. I have 42 input nodes, each one corresponding to a disc on the board which can either be occupied by red (-1), empty ...
3
votes
2answers
720 views

Hill climbing search - Map coloring problem

I have a problem like this: How to color a map with K colors such that two adjacent regions do not share a color. how can we start formulating this as a hill climbing search problem?
1
vote
0answers
53 views

Novelty Search Mutation Algorithm

I have been reading a lot lately about some very promising work coming out of Uber's AI Labs using mutation algorithms enhanced with NOVELTY SEARCH to evolve deep neural nets. https://www.arxiv-...
2
votes
0answers
108 views

Search minimum value with learning machine algorithm

I was wondering if its possible to classify or learn to estimate the minimum value in a table if the values are integer and represented 32 bits, and we can input all variable at the same moment like ...
-2
votes
1answer
282 views

How to train a simple neural network to create source code

I am thinking of making a simple and interesting research on training a RNN, to create source codes. The objective is to have a set of simple REPL programs in java, and create a source code for a ...
2
votes
2answers
623 views

Trying to make snake learn different directions

I'm really new to neural networks. I'm trying to make a neural network with genetics algorithms which will make a snake learn to look for the food and avoid hitting his tail. The thing is that I ...
1
vote
1answer
97 views

adjusted fitness in NEAT algorithm

I'm learning about NEAT from the following paper: http://nn.cs.utexas.edu/downloads/papers/stanley.ec02.pdf I'm having trouble understanding how adjusted fitness penalizes large species and prevents ...
7
votes
1answer
642 views

Neural networks vs Genetic algorithms in games like Tic Tac Toe?

Currently I'm doing a project that's about creating an AI to play the game Gomoku (It's like tic tac toe, but played on a 15*15 board and requires 5 in a row to win). I have already successfully ...
1
vote
0answers
36 views

Which algorithm would you use to solve a multiple producer-consumer problem with constraints?

I'm solving this problem similar to consumer-producer of materials (i.e. sand). This is the graph of the problem: Where Req (...
3
votes
1answer
174 views

Fitness Function altenatives in Genetic Algorithms for game AI

I have created a Gomoku(5 in a row) AI using Alpha-Beta Pruning. It makes moves on a not-so-stupid level. First, let me vaguely describe the grading function of the Alpha-Beta algorithm. When it ...
0
votes
1answer
41 views

Applied probabilistically… What does probabilistically mean?

I'm new in genetic algorithms and I'm reading the A. E. Eiben and J. E. Smith book Introduction to Evolutionary Computing (Springer 2003). On section 3.5 Recombination, page 47, second paragraph said:...
0
votes
1answer
310 views

Does fitness proportionate selection select multiple individuals?

Does fitness proportionate selection select multiple individuals? So i read on Wikipedia and on multiple stack exchange threads about fitness proportionate selection or rather roulette selection but ...
1
vote
0answers
15 views

Crossing complex and non uniform genomes?

I've been tinkering with an artificial life simulator, critterding for many years and lately ive been branching the project and adding fitness functions. Im still quiet new to genetic algorithms and ...
0
votes
2answers
39 views

Getting input about the enviorment from a game emulator [closed]

I'm starting to get into the AI field and wanted as a side project to try and make an algorithm to play old games. The problem is i need to pass everything that is happening on the screen to the ...
5
votes
3answers
453 views

Determining a fitness function for self driving car

I have been working for ages on a Neuroevolution AI program, where cars learn how to race around a track. Presently, I have a rudimentary fitness function that awards points for every degree traveled ...
4
votes
1answer
441 views

Genetic Algorithm: Is Elitism prefered in cross-over operator?

There are two potential approaches when performing cross-over operation in genetic algorithm: perform cross-over on Elites in the pool, probably the ones that are also going to be directly transfered ...
4
votes
1answer
625 views

Traveling salesman problem variant: which algorithm to choose?

I have an industrial problem which I'm trying to cast as a Traveling Salesman problem (TSP) in 3D euclidian space. There are physical limitations which implies that some subpaths may or may not be ...
2
votes
1answer
183 views

Artificial Intelligence/Machine Learning in Engineering Design

I've been looking recently into what uses AI - specifically machine learning - may have in automating engineering design. For a long time there have been algorithms that solve constraint satisfaction ...
5
votes
1answer
158 views

Advice on machine learning for a neural network

I'm aiming to create a neural network that can learn to predict the next state of a board using the rules of Conway's Game of Life. This is technically three questions, but I felt that they needed to ...
2
votes
1answer
150 views

Do genetic algorithms evolve?

After witnessing the rise of deep learning as automatic feature/pattern recognition over classic machine learning techniques, I had an insight that the more you automate at each level, the better the ...
3
votes
1answer
223 views

How can one use Genetic Algorithms to solve the “15 Puzzle” (Mystic Square)?

How would one go about solving the 15 squares puzzle using a Genetic Algorithms approach? In particular, I'd like to understand how you would represent the "chromosome" in the evolving system. That ...
4
votes
2answers
229 views

Could GA's determine fitness by “Fighting” against each other?

I am developing AI in the form of NEAT, and it has passed certain tasks like the XOR problem outlined in the NEAT Research Paper. In the XOR Problem, the fitness of a network was determined by an ...
2
votes
1answer
345 views

how to represent the weights of a neural network as binary strings for genetic algorithm

I want to train my neural network by evolution, that is I want to recombine the weights of the best performing neural networks in each evolution cycle or generation. my initial instinct was to ...
5
votes
2answers
1k views

Mutation and crossover in a genetic algorithm with real numbers

How exactly are "mutation" and "cross-over" applied in the context of a genetic algorithm based on real numbers (as opposed to just bits)? I think I understood how those two phases are applied in a "...