Brief description

The purpose of this project is to apply reinforcement learning to build a simulated vehicle navigation agent. This project involves 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.

Software and libraries

• python 2.7
• pandas
• numpy
• matplotlib
• mpl_toolkits
• pygame (https://www.pygame.org/wiki/GettingStarted)

How to clone and run the project

git clone https://github.com/QuantLandi/smartcab.git
cd smartcab
your-pdf-viewer report.pdf

Make sure you are in the top-level project directory smartcab/ (that contains this README). Then run:

python smartcab/learned_agent.py