RajGhugare19

import numpy as np 
from collections import defaultdict

# Thank you https://andyljones.com/
# Taken from https://andyljones.com/posts/rl-debugging.html#probe

class level_one_env(object):
    # One action, zero observation, one timestep long, +1 reward every timestep:
    def __init__(self, episode_length=1):
        # Set episode length