It seems that the format of the observation data changed from v1 to v2. Unfortunately, I can’t find documented anywhere what the new observation data is supposed to contain. I am interested in the global observation at first.
In v1 the global observation of each agent consisted of 4 arrays: transition map, encoding of the starting position, encoding of the ending position, encoding of the initial orientation.
Now I see there are only 3 arrays per agent. The first one seems to still be the transition map (I think). The 3rd one seems to still be the same encoding of the target position (I think). But it’s unclear what the encoding of the 2nd array is. It seems to also contain the speed of each agent, but I don’t know how to get their starting positions and initial orientation. The official documentation is really lacking: http://flatland-rl-docs.s3-website.eu-central-1.amazonaws.com/intro_observation_actions.html
Can you please point me to some examples which decode these observations (in Flatland v2) or to some explanations/documentation?
Yes we did do some major update to the vanilla observations in Flatland 2.0. We are lagging a bit behind with our documentation as the team is currently very busy trying to squash the last few bugs so we can start the next round.
class GlobalObsForRailEnv(ObservationBuilder):
"""
Gives a global observation of the entire rail environment.
The observation is composed of the following elements:
- transition map array with dimensions (env.height, env.width, 16),\
assuming 16 bits encoding of transitions.
- Two 2D arrays (map_height, map_width, 2) containing respectively the position of the given agent\
target and the positions of the other agents targets.
- A 3D array (map_height, map_width, 4) wtih
- first channel containing the agents position and direction
- second channel containing the other agents positions and diretions
- third channel containing agent malfunctions
- fourth channel containing agent fractional speeds
"""
Does this help? You can test your code using the current sparse_rail_generator but we are currently working on a fix and are hoping to push the updated version in the coming days.
Thank you for the pointers. They do help and they show me that the current encoding (for the global observation) seems wrong. For instance, the first channel of the (height, width, 4) map contains the initial direction of the current agent. But zero is both the default value and a valid value for the initial direction (which is a number from 0 to 3). So this encoding is not enough to identify the initial position of each agent.
Besides the logical issue with the encoding (which I don’t think I’m wrong about), another issue I am seeing is that it seems this (height, width, 4) map is not always fully populated for each agent. What I mean is: in the observation of each agent x, I printed all the cells (i,j) which have a non-zero value at any of the 4 channels (in the (height, width, 4) map). There should always be N (N=number of agents) cells printed by this approach, but for some agents this number is less than N (don’t know why).