How to receive both images and RAM states with the new API?

[danijar]

I'm interested in training an agent from the images while also recording the corresponding RAM states for later analysis. Previously, I have been using env._get_ram() for this purpose, but it seems that the method is no longer available. Is there a way to do this with the new API?

import gym

env = gym.make('ALE/Breakout-v5',
    obs_type='rgb',                   # ram | rgb | grayscale    <-- I would like both ram and grayscale
    frameskip=5,                      # frame skip
    mode=0,                           # game mode, see Machado et al. 2018
    difficulty=0,                     # game difficulty, see Machado et al. 2018
    repeat_action_probability=0.25,   # Sticky action probability
    full_action_space=True,           # Use all actions
    render_mode=None                  # None | human | rgb_array
)

[JesseFarebro]

Hi @danijar,

You'll still be able to get the RAM buffer by calling,

ram = env.ale.getRAM()

# OR if you want something more efficient depending on your circumstances
ram = np.empty((env.ale.getRAMSize(),), dtype=np.uint8)
env.ale.getRAM(ram)

Hope that helps!

[danijar]

Perfect, thanks!