search

LucasAlegre / sumo-rl

Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.
https://lucasalegre.github.io/sumo-rl
MIT License
746 stars 201 forks source link

issues about the reward #189

Closed way-thu closed 8 months ago

way-thu commented 8 months ago

hello Lucas, thanks for your sharing, there is one thing I feel confused, is your simulation set for a fixed total time and the simulation stops when the time reaches the total time?

LucasAlegre commented 8 months ago

Yes, the simulation runs for a fixed number of simulated seconds in sumo: https://github.com/LucasAlegre/sumo-rl/blob/main/sumo_rl/environment/env.py#L55C9-L55C21. See the documentation: https://lucasalegre.github.io/sumo-rl/documentation/sumo_env/