Lab 10 Peer Review

[LeoDardanello]

Regarding your code for the Lab 10 i've noticed some particular traits:

• Code Cleaness: the code is well suddivided into cells that covers a specific argoument or function, comments explains properly the various parameters and goals.

• Ai Training: the idea of creating two Agents, one when the Agents is using X and one when the Agent is using O, has its pros and cons. For the pros the reward process gets easier because you're only considering a single symbol, also the Q-table dimension for a single Agent is smaller compared to Q-table for an Agent that can handle both symbol. The main cons is the high specialization of each single Agent, meaning that a single Agent won't be able to play a sufficient game with X and O.

• Statistics: It could have been useful to print or plot the dimension of the Q-table for each Agent

• Interactive Interface: in my implementation i also made the user play against a Trained Agent, unfortunately i encountered some glitches maybe caused by the way i was representing the grid. I'll try to change my implementation in order to solve said glitches using your interactive_interface() function as guide.

Overall your code shows a well understanding of the Q-learning topic. Good job! Keep it up!