Problem C
RL4 Exploration vs Exploitation

Input

Your interface with the judge is the player file player.py. For this problem, look for PlayerControllerRL and ScheduleLinear classes within player.py. After editing player.py, rename it as player_4.py for submission.

A sample scenario is provided in the code skeleton (the settings.yml file). You are invited to vary the scenario by modifying the settings.yml to test your RL agent on different scenarios.

Output

The skeleton handles all the output for you. Avoid using stdin and stdout. (Use stderr for debugging.)