07 Sequential II

Sequential decisions and how do we calculate the proper policy?

After this practice session, the student

• computes the state values in simple grid worlds;
• derives the policy from known state values;
• understands the difference between state values (v) and state-action values (q).

• Discussion of the bonus quiz from the last week (prob. of reaching goal state).
• Finding the optimal policy using value iteration and policy iteration.
• Introduction of the bonus quiz for the next week (policy evaluation).

[See pdf]

Policy evaluation on a small map.

• 0.5 points
• submit your solution to BRUTE lab07quiz, deadline in BRUTE
• format: text file, photo of your solution on paper, pdf - what is convenient for you
• solution will be discussed on the next lab
• Students with their family name starting from A to K (included) have to solve and upload subject A , while students with family name from L to Z have to solve and upload subject B.

• Finish and submit the bonus quiz, lab07quiz.
• Work on the Markov decision processes semestral task.