Skip to content

Applied reinforcement learning to build a simulated vehicle navigation agent. This project involved modeling a complex control problem in terms of limited available inputs, and designing a scheme to automatically learn an optimal driving strategy based on rewards and penalties.

Notifications You must be signed in to change notification settings

miguelangelnieto/Train-a-Smartcab-to-Drive

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Train a Smartcab to Drive

Part of the Machine Learning Nanodegree Program.

Applied reinforcement learning to build a simulated vehicle navigation agent. This project involved modeling a complex control problem in terms of limited available inputs, and designing a scheme to automatically learn an optimal driving strategy based on rewards and penalties.

  • Reinforcement Learning
  • Q-Learning
  • Optimization
  • Modeling
  • Model Tuning
  • Python
  • Algebra
  • Statistics
  • Calculus

Home Page

LinkedIn

About

Applied reinforcement learning to build a simulated vehicle navigation agent. This project involved modeling a complex control problem in terms of limited available inputs, and designing a scheme to automatically learn an optimal driving strategy based on rewards and penalties.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published