Intermediate · Reinforcement Learning

Reinforcement Learning Agent

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. The entity that makes decisions and performs actions in an environment to maximize cumulative rewards.

Technical Definition

The entity that makes decisions and performs actions in an environment to maximize cumulative rewards.

How it works

In reinforcement learning, the agent is the intelligent entity that interacts with its environment. It observes the state of the environment, chooses an action to take, and receives a reward or penalty as a consequence. Through repeated interactions, the agent learns an optimal policy to achieve its goal by maximizing cumulative rewards over time.

Related Concepts

• Reinforcement Learning — A paradigm where an agent learns to make decisions by receiving rewards or penalties from its environment through trial and error.
• Environment — The external world or system with which an agent in reinforcement learning interacts and receives feedback.
• Reward — A feedback signal in reinforcement learning, indicating the desirability of an agent's action in a given state.