grantsrb / gym-snake Goto Github PK

This is what I get when I train it on DQN

Traceback (most recent call last):
File "C:\Users\mahes\anaconda3\lib\site-packages\gym\utils\closer.py", line 67, in close
closeable.close()
File "C:\Users\mahes\anaconda3\lib\site-packages\gym\core.py", line 188, in close
self.render(close=True)
File "C:\Users\mahes\Gym-Snake\gym_snake\envs\snake_extrahard_env.py", line 44, in render
self.viewer.imshow(self.last_obs)
File "C:\Users\mahes\anaconda3\lib\site-packages\matplotlib_init_.py", line 1492, in inner
return func(ax, *map(sanitize_sequence, args), **kwargs)
File "C:\Users\mahes\anaconda3\lib\site-packages\matplotlib\axes_axes.py", line 5756, in imshow
im.set_data(X)
File "C:\Users\mahes\anaconda3\lib\site-packages\matplotlib\image.py", line 723, in set_data
self._A = self._normalize_image_array(A)
File "C:\Users\mahes\anaconda3\lib\site-packages\matplotlib\image.py", line 693, in _normalize_image_array
raise TypeError(f"Invalid shape {A.shape} for image data")
TypeError: Invalid shape (8,) for image data
Exception ignored in: <function Env.del at 0x000001E853F6D4C0>
Traceback (most recent call last):
File "C:\Users\mahes\anaconda3\lib\site-packages\gym\core.py", line 252, in del
File "C:\Users\mahes\anaconda3\lib\site-packages\gym\core.py", line 188, in close
File "C:\Users\mahes\Gym-Snake\gym_snake\envs\snake_extrahard_env.py", line 43, in render
File "C:\Users\mahes\anaconda3\lib\site-packages\matplotlib\axes_base.py", line 1388, in clear
File "C:\Users\mahes\anaconda3\lib\site-packages\matplotlib\axes_base.py", line 1271, in __clear
File "C:\Users\mahes\anaconda3\lib\site-packages\matplotlib\axis.py", line 895, in clear
File "C:\Users\mahes\anaconda3\lib\site-packages\matplotlib\text.py", line 175, in _reset_visual_defaults
AttributeError: 'NoneType' object has no attribute '_val_or_rc'

Hello. I found this seemingly flexible and aesthetic implementation of snake, and I wanted to try it out as soon as I could before training any model.

So, using the following code, I try to render a game with random movements gained from env.action_space.sample(), but what happens is only the first frame renders, and I get
<Figure size 576x396 with 0 Axes> returned for every frame thereafter.

Other OpenAI gym environments render correctly for me, so what am I doing wrong, or is this a bug?

My code:

import gym
import gym_snake

## Creating environment
env = gym.make('snake-v0')
obs = env.reset()

## Observing snake for now
obs = env.reset()

for _ in range(5): # run for 1000 steps
    env.render() # Render latest instance of game
    action = [env.action_space.sample()] # Random action
    env.step(action) # Implement action
    
env.close()

It would be nice to be able to flatten the images to greyscale by averaging across the 3rd dimension in the observation array (i.e. reduce to a lower dimension), but currently the food colour becomes the same as the grid colour (85).

I tried changing this:
grid_object.FOOD_COLOR = [0,0,0] # Color of food units

But it seemed to have no effect?