​How to start Basic Refinement Learning in Traffic Control?

[Lion1989x]

[ FlexSim 23.2.2 ]

How to start basic refinement learning in Traffic Control?

- Waiting Time

- North - Red / Green Time ?

- East - Red / Green Time ?

- South - Red / Green Time ?

- West - Red / Green Time ?

This is my file.

15.fsm

[kavika_faleumuE6HT5]

@Lion, what is your objective with this model? What are you trying to have a RL solve here?

[jeanette_fullmer88DK3]

Hi @Lion,

We haven't heard back from you. Were you able to solve your problem? If so, please add and accept an answer to let others know the solution. Or please respond to the previous comment so that we can continue to help you.

If we don't hear back in the next 3 business days, we'll assume you were able to solve your problem and we'll close this case in our tracker. You can always comment back at any time to reopen your question, or you can contact your local FlexSim distributor for phone or email help.

[Lion1989x]

I apologize adout that . I have returned to continue this research.

[Lion1989x]

Objective is Minimize waiting times By adjusting the timing of traffic lights.

I want RL to learn traffic patterns and appropriate signal timing.

[kavika_faleumuE6HT5 · Accepted solution]

@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.