Introduction
Reinforcement learning is a subset of machine learning, where AI agents learn from the environment by interacting with it and improving their performance. This branch of AI learns by trial and error instead of human supervision. The following diagram illustrates how an AI agent acts on the environment and receives feedback after each action. Feedback is made up of two parts: reward and the next state of the environment. Rewards are defined by a human:
Google's DeepMind published a paper in 2013 about Playing Atari with Deep Reinforcement Learning. In this paper, a new algorithm called Deep Q Network (DQN). It explains how an AI agent can learn to play games by just observing the screen without any prior information about the game. The result of the experiment turned out to be pretty impressive in terms of accuracy. It opened the era of what is called deep reinforcement learning, a mix of deep learning and reinforcement learning.
The Q-Learning algorithm has a function called Q...
