Hands-On Neuroevolution with Python

Agents records store

After completing the experiment, we are interested in evaluating and visualizing how each individual solver agent performed during the evolutionary process through all generations. This is accomplished by collecting additional statistical data about each agent after running the maze-solving simulation for a specified number of time steps. The collection of agent records is mediated by two Python classes: AgentRecord and AgentRecordStore.

The AgentRecord class consists of several data fields, as can be seen in the class constructor:

    def __init__(self, generation, agent_id):        self.generation = generation        self.agent_id = agent_id        self.x = -1        self.y = -1        self.fitness = -1        self.hit_exit = False        self.species_id = -1 self.species_age ...