RLAI Reinforcement Learning and Artificial Intelligence (RLAI)
Chapter 4 Programming Exercise

Programming Exercises (The Party Problem - Dynamic Programming):

    Due: Tuesday, October 19th

You will need the party problem and dynamic programming code.

Tasks

  1. Write a function implementing value iteration (using policyiteration from the provided code as example)
  2. Run it on the party problem
  3. Print out the value function after each sweep
  4. Hand in:
    1. Your value iteration code (not the whole program, just the valueiteration function)
    2. The results from task 3 above

    Submission instructions

Please hand in a hard copy in class.

Back to main page