Skip to content

LeparaLaMapara/RL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Reinforcement Learning Concepts

Welcome to the beginner's guide to understanding the fundamental concepts of Reinforcement Learning (RL). This guide will break down key RL concepts in simple terms with relatable examples.

Table of Contents

Agent

An agent is like the central character in the world of RL. It's the decision-maker that interacts with its environment to achieve its goals.

Example

Imagine training a robot to navigate a maze. The robot is the agent, making choices on how to move to find the maze's exit.

Environment

The environment is the stage where the RL drama unfolds. It's everything outside the agent that the agent can perceive and interact with.

Example

In the maze scenario, the environment encompasses the maze itself - the walls, paths, and the exit. The robot (agent) interacts with this maze.

State

A state is like a snapshot of the environment at a particular moment. It encapsulates all the information the agent needs to make decisions.

Example

In the maze, a state would involve the robot's current position, nearby walls, and distance to the exit. This information guides the robot's movement choices.

Action

Actions are the decisions the agent takes to transition between states. These are the agent's way of affecting the environment.

Example

In the maze, the robot's actions are its movements: up, down, left, or right at each intersection.

Reward

Rewards are the agent's feedback for its actions. They indicate how good or bad an action was in terms of achieving the agent's goal.

Example

In the maze, moving closer to the exit yields positive rewards, while hitting walls results in negative rewards. The goal is to maximize cumulative rewards.


Feel free to refer to this guide as you delve into the world of Reinforcement Learning. Understanding these core concepts will provide a solid foundation for your journey into more advanced topics and applications.

About

Introductions to Reiforcement learning

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published