SimAnt Simulation Using NEAT
نویسندگان
چکیده
In nature, ants in a colony often work together to complete a common task. We want to see if we can simulate this phenomenon. We create a simulation that looks at predator prey interactions based o↵ of the 1991 SimAnt game. In this game a spider attempts to eat individual ants from a colony, but if the ants form a large enough swarm they can work together to eat the spider. The question we are attempting to answer is: Will an ant colony (the prey) learn to swarm together to kill a spider (the predator)? We hypothesize that the ants will learn to swarm and learn to kill the spider as well. To test our hypothesis we run a number of simulation experiments using a hard coded spider and a colony of ten ants who all have the same brain. Their brain evolves over several generations using a program called NeuroEvolution of Augmenting Topologies (NEAT) [6]. The fitness score is determined by how many ants in the colony survive with an added bonus to the fitness score if a large enough swarm is able to kill the spider. The outcome of these experiments supports our hypothesis. After several generations we observe the behavior of ants swarming together and trying to kill the spider. Our numerical evidence shows a positive trend over ten generations of evolution, both for fitness scores and for spider deaths, which further supports our hypothesis. These findings suggest that the prey learn the behavior of working together not only to avoid getting eaten by the spider, but also to kill the spider.
منابع مشابه
Evolving Mario to Maximize Coin Score Using Neat and Novelty
Genetic algorithms can be used to evolve agents that will complete game tasks in a given game environment. In this paper, we discuss our experimental results using NEAT and Novelty to evolve Mario, from the popular game Super Mario Bros, to maximize his coin score. To conduct our experiments, we developed our own Mario simulator, creating a small world and a big world. Each world has an easy an...
متن کاملComparing Adaptivity of Ants using NEAT and rtNEAT
Although individual ants have an extremely basic intelligence, and are completely incapable of surviving on their own, colonies of ants can develop remarkably sophisticated and biologically successful behavior. This paper discusses a set of experiments which attempt to simulate one of these behaviors, namely the ability of ants to place pheromones as a way of communication. These experiments in...
متن کاملExtending Robot Soccer Using NEAT
Robot soccer is an active research area that offers a challenging research domain to investigate a large spectrum of issues relevant to the development of complete autonomous agents. We used a two‐ and three‐agent robotic soccer simulation to study a coevolutionary learning technique: NeuroEvolution of Augmenting Topologies (NEAT). Our aim is to figure out a good fitness function for the robot ...
متن کاملNeato Quadcopters
In this paper we detail the implementation and execution of an unsuccessful experiment involving simulated quadcopters trained using NEAT. Quadcopters are simulated using the robotics framework ROS, with the physics simulator Gazebo and the packages provided by Team Hector Darmstadt, and the controllers are implemented using neural networks. Unfortunately, the current experiments failed due to ...
متن کامل