In order to help determine success, the ant now has a limited lifespan. A dead ant is marked by a red square. The neural network will be trained to progress outward and locate food to replenish energy.
Used RxJS to create an observable in the ant model which triggers an action intent (for now, just “move” and “turn”). The environment subscribes to the intent determines the result of the ant’s action. If the action is successful, e.g. the ant moves forward, a corresponding positive response is returned. If the action is unsuccessful,… Read the full article