Ray Perception 3D Sensor and MA-POCA Neural Networks

[ongr1996_unity]

I am currently using Ray Perception to tag other agents in the environment and walls , so agents learn to avoid collision. After looking through documentation and other posts, the conclusion I came to was that the rays are able to detect tags and return a normalized value between 0 and 1 depending on the distance the tagged object is hit.

Q1) Does that mean if two agents are standing right next to each other then the ray is outputting a number extremely close to 1? Also, this is accessible infromation correct ?

I wanted to use the information from Ray Sensors’ Stacked Vectors to create a discrete action that utilizes this information. For example, grab a value for the distance between two agents (on the stacked vector, let’s say 5) and then compare it to the distance between two agents (at stacked vector 0).

Q2) Is this possible or do I have to use a different sensor (I understand that it won’t be the actual relative distance because RP sensors data)? If so, how exactly can I access this data and are there examples?

[ongr1996_unity]

For anyone interested in utilizing the Ray Perception Sensor 3D Sensor outputs , here is another post that helped clarify on the outputs to Ray Perception.

Getting the Detectable Tags from ray perception sensor script

I have an enemy tag in the RPS script and i want to do an if statement inside my agent script to say if the ray cast hits an object with the tag enemy then do something. I am not sure however how to actually retrieve the detectable tag info from the RPS script. Any help would be great as I am fairly new to this.