question

@Lion, when setting up your model, you should keep in mind some key concepts about RL.

Primarily, you should identify:

• What observations are going to be available to your agent? (Stay-time of cars in line?)
• What constitutes a "reward" and when will it be given? (Maybe you give higher rewards for sending cars through that have been waiting the longest, keeping track of staytime on the car with a label or by pushing them to a list)
• What actions do you want the agent to control? (Just switching the traffic lights?)

Once you've made these decisions, then you can start setting up the environment as outlined in the documentation.