Skip to content

Latest commit

 

History

History
19 lines (12 loc) · 1.21 KB

README.md

File metadata and controls

19 lines (12 loc) · 1.21 KB

Reinforcement Learning

Train a Smartcab How to Drive

SmartCar is a demonstration of the Q-Learning methodology of training a smart car to navigate and find directions to its destination. At the beginning, the smart car will be placed at a random location on a 8x6 street grid and another random location will be designated as a destination. The smart car will also be supplied with a waypoint indicating a recommended direction of travel to reach the destination. However, the car will be required to obey the traffic signals and will incur penalties for trying to violate them. The goal of this simulation is to get the cab to reach its destination before it runs out of time and to train it to reach its destination as quickly as possible.

Install

This project requires Python 2.7 with the pygame library installed

Run

In a terminal or command window, navigate to the top-level project directory smartcab/ (that contains this README) and run the following commands:

$ git clone http://github.com/adityasiwan/Machinelearning-smartcar.git
$ cd smartcar
python smartcab/agent.py

This will run the agent.py file and execute your agent code.