Question about env.step(action) return value.

[kautenja]

Question about env.step(action) return value.

[Kautenja]

I'll need more information to understand why this is happening. Validate your version is 3.1.0 or later using the following:

import pkg_resources
print(pkg_resources.get_distribution("gym-super-mario-bros").version)

If you are running any version of gym-super-mario-bros below 3.1.0, info will not contain anything and you should upgrade using python -m pip install gym-super-mario-bros -U

If you are running version 3.1.0, 3.1.1, or 3.1.2, please run the following and provide the output:

import gym_super_mario_bros
env = gym_super_mario_bros.make('SuperMarioBros-v0')
_ = env.reset()
_, _, _, i = env.step(0)
print(i)

Using 3.1.2 on Windows 10 I get {'flag_get': False} as the output (which is expected).

[leaderj1001]

Answer thank you so much.
But, I want to get a distance information and time information.
Could I get that information?

[Kautenja]

version 4.0.0 has been released to address your issue (among others). Please see the below table for the new table of values offered in the info dictionary:

Key	Type	Description
coins	int	The number of collected coins
flag_get	bool	True if Mario reached a flag or ax
life	int	The current life (i.e., {3, 2, 1})
score	int	The cumulative in-game score
stage	int	The current stage (i.e., {1, ..., 4})
time	int	The time left on the clock
world	int	The current world (i.e., {1, ..., 8})
x_pos	int	Mario's x position in the stage

Does this resolve your issue?

[leaderj1001]

Wooooow!!! It was super greatest update for me!!
Thank you so much :) Now I can using super-mario deep learning easily.
I really appreciate 👍