Glossary

Reinforcement learning is a potent branch of machine learning, where software agents determine the ideal behavior within a context to maximize cumulative rewards. It encapsulates learning via trial and error, and interaction with its environment, which is instrumental in discovering the most rewarding actions.

Reinforcement Learning Theory is a field of machine learning. It determines the actions of agents to maximize rewards. It has roots in psychology and utilizes dynamic programming, Monte Carlo methods, and temporal difference learning.

A reinforcement learning algorithm, Q Learning, calculates the ‘quality’ or value of actions, aiding in achieving future rewards. Ideal for handling stochastic transition and increased reward problems.