Vector Observation contents

#1

Hi @arthurj

What information is now stored in the vector observation?

In v1.3 I think it was the remaining time and if the agent has a key or not.

Now it looks like that there are 8 values:

Vector Observation space size (per agent): 8

#2

Judging by this function in obstacle_tower_env, the first six elements are for the number of keys (Perhaps one-hot? Not sure). Seventh is the time remaining and eight is the floor number, as in v1.3.

#3

That is correct. We now provide the floor number as a vector observation, for those interested in using it for logging purposes, or for input to the agent itself.

#4

I just printed the contents of the vector observation.
It has a shape of (4).
The first element is the visual observation (168, 168, 3).
The remaining items have a shape of () and hold the values key, time and current floor.

How does this relate to a vector observation size of 8.

Just to clarify, I’m on v2.0 and retro mode is disabled.

1 Like
#5

Time and current floor each use one value, the other six are used by the key parameter.

#6

So how is it possible that I only get 3 values for the vector observation and not 8?
Like said before I’m using the latest build and obstacle_tower_env.

#7

Well I do see 8:
array([[1.00e+00, 0.00e+00, 0.00e+00, 0.00e+00, 0.00e+00, 0.00e+00, 2.99e+03, 0.00e+00]])

Maybe check the reset parameters?

#8

I just upgraded to v2.1 and completely reinstalled my Python environment and the bug still exists.

Also, the value of the current floor is always equal to 0.

I observed this on windows and ubuntu.

#9

Apologies if this sounds bit naive, but make sure you are importing the correct Python libraries. E.g. do you have obstacle_tower_env.py file in the directory from which you run the experiments?

You can find the imported file with the following:

In [1]: import obstacle_tower_env                                                                                                                           

In [2]: obstacle_tower_env.__file__                                                                                                                         
Out[2]: '/home/USERNAME/.local/lib/python3.5/site-packages/obstacle_tower_env.py'
#10

If everything else is correct, possibly a windows issue- I’m using ubuntu 16.04 btw

#11

I checked the path of obstacle_tower_env.py and replaced the file with the one from the repository.
Same issue.

I tested this on two Ubuntu and two Windows machines. All have the same behavior.

#12

Hi,@arthurj the obs[0:6] is the observation of keys, but my question is how does it relate to the number of keys?

I check the obs value in debug mode, even when I haven’t got any key the value is [1,0,0,0,0,0]

#13

Looking at how ObstacleTowerEnv handles this observation, the vector tells number of keys as one-hot encoding (or with 1s up till number of keys, e.g. two keys would be [1,1,1,0,0,0]). So [1,0,0,0,0,0] means zero keys.

#14

So this means in higher floor, there might be two keys and either of the keys can be used interchangeably?

Another question, why doesn’t just use 1 value to pass observation like [2] for two keys?

#15

Does anybody have any idea on how to debug my issue?