Developing Frogger Player Intelligence Using NEAT and a Score Driven Fitness Function
نویسندگان
چکیده
In this report, we examine the plausibility of implementing a NEAT-based solution to solve different variations of the classic arcade game Frogger. To accomplish this goal, we created a basic 16x16 grid that consisted of a frog and a start, traffic, river, and goal zone. We conducted three experiments in this study on three slightly different versions of this world, all of which tested whether or not our robot (the frog) could learn how to safely navigate from the start zone to the goal zone. However, this was not an easy task for our frog, as it needed to learn how to avoid colliding with obstacles in the traffic part of the world, while it also needed to learn how to remain on the logs in the river section of the world. Accordingly, we equipped our frog with 11 sensors that it could use to detect obstacles it needed to dodge and obstacles it needed to seek, and we also gave our frog one extra sensor that provided it a sense of it’s position in the world. In all three experiments, a fitness function was used that exponentially rewarded our frog for moving closer to the goal zone. In addition, we used a genetic algorithm called NEAT to evolve the weights of the connections and the topology of the neural networks that controlled our frog. We ran each experiment five times, and it was seen that NEAT was able to consistently find optimal solutions in all three experiments in under 100 generations. As a result, we deem that we were able to successfully demonstrate our method’s ability to solve multiple representations of the classic arcade game Frogger.
منابع مشابه
Extending 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 کاملA Neuroevolution Approach to Imitating Human-Like Play in Ms. Pac-Man Video Game
Simulating human behaviour when playing computer games has been recently proposed as a challenge for researchers on Artificial Intelligence. As part of our exploration of approaches that perform well both in terms of the instrumental similarity measure and the phenomenological evaluation by human spectators, we are developing virtual players using Neuroevolution. This is a form of Machine Learn...
متن کاملSimAnt Simulation Using NEAT
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 ...
متن کاملRedesigning a CD Player for Intuitive Rich Interaction
This paper presents a redesign of a CD player, a combination of creative and analytical processes. After an analysis with users of the product and its functionalities, the interaction relabelling technique was used to explore richness of actions, while the Frogger framework was used to design for intuitiveness. The resulting ideas were translated into interactive prototypes, involving functiona...
متن کاملFitness Functions in NEAT-Evolved Maze Solving Robots
In this paper, we examine the effect of fitness functions on the ability of a robot evolved with NEAT (NeuroEvolution of Augmenting Topologies) to find a light in a simple maze. By varying the fitness function used to determine a genotype’s likelihood of persisting in the next generation, we propose to look at how a robot’s solution to a task is influenced by the prevalence of intermediate and ...
متن کامل