08 Reinforcement Learning I

We don't know the model of the robot-agent; it's behaving somewhat strangely, the path to the goal is unknown, with some traps along the way: what do we do?

Traditional quiz: calculate Q values from training episodes using direct evaluation.

Finish the Markov decision process assignment: deadline at the end of the week.

Start working on the Reinforcement Learning assignment, deadline on BRUTE.

• Mystery game video, that was at the beginning of the lecture.