Key Concepts of Modern Reinforcement Learning

An Introduction to Reinforcement Learning

The fundamental level of a reinforcement learning setting consists of an Agent interacting with an Environment in a feedback loop. The Agent selects an action for each state at time s_tof the Environment based on the response that it received from the Environment in the previous state at time s_{t-1}. From this basic setup, we can already identify two principal components in a reinforcement learning setting, which is the Agent and the Environment.