gistfile1.txt

class CustomEnvironment(Environment):

    def __init__(self):
        super().__init__()

    def states(self):
        return dict(type='float', shape=(8,))

    def actions(self):
        return dict(type='int', num_values=4)

    # Optional, should only be defined if environment has a natural maximum
    # episode length
    def max_episode_timesteps(self):
        return super().max_episode_timesteps()

    # Optional
    def close(self):
        super().close()

    def reset(self):
        state = np.random.random(size=(8,))
        return state

    def execute(self, actions):
        next_state = np.random.random(size=(8,))
        terminal = np.random.random() < 0.5
        reward = np.random.random()
        return next_state, terminal, reward