The difference between Reinforcement Learning and Deep-learning

Deep learning (DL) algorithms look for to iteratively minimize a certain loss function to indicates the accuracy of a functional representation of a system. Typically assumes that the data it works with is independent and identically distributed (IID) and with a stationary distribution. DL is a subfield of machine learning (ML), essentially, it solves the problem of classification and regression. Neural Networks, the main method it uses is just a type of mathematical models.

Reinforcement learning (RL) agents, on the other hand, looks for to iteratively maximize a certain notion of a numerical reward obtained through continued interaction with its environment. RL is one of the types of machine learning and also a branch of Artificial intelligence (AI). In this type of machine learning, the machine itself learn how to behave in the environment by performing actions and comparing with the results. It is like a machine performing trial and error method to determine the best action possible based on the experience. Reinforcement learning involves goal-oriented algorithms, which attain a complex goal with multiple steps which ultimately improves the performance of the machine to predict things.

Modern days neural networks (NN) are the solution to most of the complex problems in Artificial intelligence like Computer vision, machine translation etc. If Neural networks combined with reinforcement learning, then it is very easy to solve even more complex problems. This way of integrating neural networks with reinforcement learning is known as Deep Reinforcement learning.

Reinforcement learning involves the below-mentioned terms:

Agent: One who performs the action. In the case of games, the character of the game player is an agent.

Action: It is the step the agent performs to achieve the reward.

Rewards: These are given to the agent on reaching the particular level or performing a particular action. Rewards are considered as the measure of success.

Environment: This is the world where the agent performs actions.

State: It is the immediate or the present situation of the agent.

Deep Reinforcement learning helps to solve various complex problems in real life like self-driving cars, complex video games etc.

Whereas DL is used for applications with large datasets.