Popular Courses
Beginner – Linear Regression
Introduction
Beginner – Decision Trees
Introduction
Beginner – Neural Networks
Introduction

Sign in to Curvingo

or

New Account     Reset Password     

Plans

Details
Reinforcement Learning
Introduction
Simulation
Line World
Grid World
Where Do We Go From Here?
Code with Python
Summary
Curvingo · Made in India

Share

Send us Feedback

Please let us know if you have any feedback and suggestions, or if you find any errors and bugs in our content.

Sorry, your message couldn’t be submitted. Please try again!

Thanks for your feedback!

Reset Progress

This will delete your progress and chat data for all chapters in this course, and cannot be undone!

Glossary

Select one of the keywords on the left…

Reinforcement LearningWhere Do We Go From Here?

Reading time: ~5 min

You have seen how far a few simple rules go. An agent that explores, collects rewards and nudges its estimates found the best jalebi stall, learned the way down a lane, and found a route through a maze you built — without anyone programming the answer.

The same loop of runs in robots that learn to walk, in warehouse robots that plan their routes, in programs that beat world champions at chess and Go, and in the training of chatbots, where people's ratings of the answers act as the reward.

Tip

An agent learns exactly what the reward asks for — nothing more. In one well-known experiment, a boat-racing agent discovered it could score more points by circling round and hitting the same targets again and again than by finishing the race. Designing the reward carefully is half the job.

Speed Round: Name the Part

Get five right to move on.

Sina