During my master's program, I had the chance to take a really useful class on reinforcement learning, even though it was meant for Ph.D. students. You can find the term paper and exercises from that class here. Each exercise has its own document for download, and you can also learn more about the term paper by clicking [here].
Please note that the documents are in Persian, as the course was taught in Persian.
This exercise focuses on finding the optimal path to reach the destination in a spiral grid using temporal difference learning methods, including Q-learning and SARSA. You can download the related document by clicking on the link provided.
In this exercise, I utilized the Monte Carlo method to determine the optimal path for a car within a field, considering speed constraints.
This exercise employs dynamic programming to calculate the optimal policy for an agent to reach the goal state in a hypothetical problem space representing a frozen lake.
