INNER CODE UNIT · Python
sample
maxpumperla/learning_ray · notebooks/maze_gym_env.py:13
def sample(self):
return random.randint(0, self.n - 1)
class Environment:
seeker, goal = (0, 0), (4, 4)
info = {'seeker': seeker, 'goal': goal}
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)