Percentage Points (of final grade): 7.
Individual work: You should do this assignment alone.
Referring to Control Assignment 1, implement a reinforcement learner that can do what you learned in PART-1 of that assignment (piloting the alien space ship off the planet), i.e. learn to keep the thrust in a 1000-point range for 5 seconds. This will be done in two parts:
First, write a detailed specification/report (max 4 pages) detailing everything about how you would go about implementing such a reinforcement learner for that task. The description must be detailed enough that it could be given to your fellow student to implement, and they would not have to second-guess any key detail of the design. Make sure to note any challenges or limitations that, compared with human performance on the task, are implied by or inherent in your design. You may use any reinforcement learning mechanism of your choice (Q-learning, SARSA, etc.).
Using the Matlab/Simulink implementation of the Alien Spaceship task, implement the reinforcement learner described in your specification from Part 1.