What is Reinforcement Learning (RL)

Reinforcement learning is one of the three basic paradigms of machine learning. The other two being Supervised Learning and Unsupervised Learning. It is an autonomous self-learning system that learns from trial and error. It is different from Supervised learning because unlike supervised learning it is not fed with labelled input/out training data. It works on the principle of rewarding desired behavior and penalizing undesired one. Over time through this feedback, the system learns and optimizes its behavior to get maximum reward.

Reinforcement Learning has an agent or learner that interacts with an environment under rules that the agent follows and takes actions which get rewarded either positively or negatively.