Why you should do this Guided Project

Deep Blue a chess computer beat world chess champion Garry Kasparov in 1997. The game of Go is played on a 19 by 19 board and is much more difficult to play as there are about 10 to the power 360 different combinations. It was thought it would take decades before a computer beat a Go champion. But now, thanks to reinforcement learning, computers can easily beat Go champions, beat Chess Grandmasters and outperform Humans in every game. In this project, you will use Monte Carlo Reinforcement learning algorithms for the simple game Frozen lake. You will quickly grape import concepts of Reinforcement learning and apply open AI's  gym, the go-to framework for Reinforcement learning.

For example, the agent will be able to guide itself through a simple environment: Frozen-Lake-Game-Iteration.gif 738 KB

A Look at the Project Ahead

• Work with an OpenAI Gym environments
• Explain what Reinforcement Learning is
• Explain what Monte Carlo Method is
• Create an agent that uses Monte Carlo Method to play Frozen Lake
• Train and Test the agents using the Frozen Lake environment
• Improve and update your algorithm.

What You'll Need

• Knowledge of python programming language.

Frequently Asked Questions

• Do I need to install any software to participate in this project?
  Everything you need to complete this project will be provided to you via the Skills Network Labs and it will all be available via a standard web browser.
  
  
  
• What web browser should I use?
  The Skills Network Labs platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer, or Safari.