Reinforcement Learning

Reinforcement learning is the most advanced part of machine learning which is inspired by behaviourist psychology and neuroscience.

In reinforcement learning the goal is for an agent in a state to perform actions to maximise future reward.

This is done by balancing two techniques, exploration and exploitation. Exploration is related to exploring the world to figure out better ways of doing things in the world. Exploitation is the process of using the knowledge gained through exploration to increase the reward by finding better states and actions with higher rewards.