ClassroomThe classroom
Back to the lesson libraryMECHANISM · 13 MIN
M24.1 CONNECT THE MECHANISM

Learn decisions from consequences over time

A robot vacuum gets no instructions, only a reward when it reaches its dock. Meet the agent, its actions, and its rewards, and see why a good move can pay off only later.

LESSON OVERVIEW13 min lesson

Lesson overview

A robot vacuum gets no instructions, only a reward when it reaches its dock. Meet the agent, its actions, and its rewards, and see why a good move can pay off only later.

What you’ll explore

  • Reinforcement learning connects observations, actions, rewards, and future consequences; a policy aims to improve expected return under a defined environment and interaction budget.
GO TO THE SOURCE

Original explanations, connected to the research.

Reinforcement Learning: An Introduction, 2nd edition (Sutton & Barto, 2018)Dive into Deep Learning — reinforcement learningHuman-level control through deep reinforcement learning (Mnih et al., Nature 2015)
Suggest a correction

A precise note can make an explanation better.

Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.

The file includes this note, the scene title, and lesson metadata. Your saved progress and quiz responses are excluded. Download before leaving or reloading to keep your note.