Simulation of the agent's learning behavior in a dynamically changing environment. The goal of the agent's behavior is to find and consume food. Search efficiency increases in the process of continuous interaction of the agent with the environment. A model-free reinforcement learning algorithm, Q-learning, is used as the learning algorithm. Program is written in C (using Win32API).
Circles packaging simulation code in this project is available under the GPLv3 license. You can find the license file here: LICENSE