Reinforcement learning, in which an agent learns to make decisions by interacting with the environment, has really taken off in the last few years. It is one of the hottest topics in artificial intelligence and machine learning these days, and research in this domain is progressing at a fast pace. In reinforcement learning (RL), an agent converts their actions and experiences into learning to make better decisions in the future.
Reinforcement learning doesn't fall under the supervised or unsupervised machine learning paradigm, as it is a field in its own right. In supervised learning, we try to learn a mapping F: X → Y that maps input X to output Y, whereas in reinforcement learning, the agent learns to take the best action through trial and error. When an agent performs a task well, a reward is assigned, whereas...
