INNER CODE UNIT · Python
__init__
maxpumperla/learning_ray · notebooks/maze_gym_env.py:22
def __init__(self, *args, **kwargs):
self.action_space = Discrete(4)
self.observation_space = Discrete(5*5)
def reset(self):
"""Reset seeker and goal positions, return observations."""
self.seeker = (0, 0)
self.goal = (4, 4)
return self.get_observation()
def get_observation(self):
"""Encode the seeker position as integer"""
return 5 * self.seeker[0] + self.seeker[1]
def get_reward(self):
"""Reward finding the goal"""
return 1 if self.seeker == self.goal else 0