Resolved Environment Definition

I am looking for a definition of enviroment in RL.
I found this "Learning Environment - which contains the Unity scene and all the game characters. The Unity scene provides the environment in which agents observe, act, and learn. How you set up the Unity scene to serve as a learning environment really depends on your goal. You may be trying to solve a specific reinforcement learning problem of limited scope, in which case you can use the same scene for both training and for testing trained agents. Or, you may be training agents to operate in a complex game or simulation. In this case, it might be more efficient and practical to create a purpose-built training scene. The ML-Agents Toolkit includes an ML-Agents Unity SDK (com.unity.ml-agents package) that enables you to transform any Unity scene into a learning environment by defining the agents and their behaviors"
However, I am not refering in Unity, most as a term in AI.
Can some define it?

 

Environment covers everything that agent doesn't have direct control on it. The line between agent and environment is determined by the designer of the environment. Think about driving a car on a road. you can think the environment the road and the agent is the car if you only want to observe the relationship of the car with the road. You can increase the complexity and change the definition of the environment by saying well humans doesnt have direct control on the car, they use steering So the car is also a part of the environment now. As you can see this depends on which perspective do you see the example. One can go extreme and say, my agent doesnt have the perfect control of it's body (for instance hands which drive the car) Therefore your agent is your brain, everything else is part of the environment.

 

Wow, thank you that really helped me!