For this weeks discussion, you will spend some time applying what you have learned about reinforcement learning.

In your initial post, address the following:

• Design a set of states, rewards, and rules for an intelligent agent playing a simple board game. You may choose any board game that you are familiar with. In your design, be sure to consider the following:
  • States, including starting and ending states, and possible actions
  • Rewards or penalties for reaching a state
  • Rules for navigating from one state to another
• Compare your approach to the Markov Decision Process (MDP) that you learned about in this module. What similarities and differences do you see between your approach and the MDP?

In your response posts to your peers, address the following:

• Evaluate the thoroughness of your classmates designs. What did they do well? Were there any states that they missed? Do their rewards and penalties make sense, and help move the agent to the goal?