Replies: 1 comment
-
Hi, sumo-rl follows the more general formulation in the RL literature where the actions correspond to any traffic phase without a specific order. Changing the actions to be only {keep, change} the current phase should be easy to implement. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello.
I am currently looking to use SUMO to perform signal control with DQN at a single intersection.
However, when learning, it does not learn the signals in the same order as set in the network file.
How can I train it to change only the time without changing the order of the signals set in the network file?
Beta Was this translation helpful? Give feedback.
All reactions