SOLVING A TWO DIMENSIONAL ENVIRONMENT WITH REINFORCEMENT LEARNING

Reinforcement learning (RL) is a branch of machine learning that studies how intelligent agents should operate in a given environment in order to maximise cumulative reward. Along with supervised and unsupervised learning, reinforcement learning is one of three basic machine learning paradigms. and unsupervised learning. In this project, we show how to make a Reinforcement Learning agent learn in any environment that it is put in and demonstrate why Q-learning is not advisable to use in a high dimension environment or an environment with continuous observation space with relatively big intervals. In this process, we will come across OpenAI/Gym and stablebaselines3 in implementing the above concept To ease usage, we have also developed a Graphical Interface using the PyQt Library, a ported version from the c++ Qt library to python.