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

_compute_dones wrong? #132

Closed Crystal-Spider closed 1 year ago

Crystal-Spider commented 1 year ago

Hi, I noticed that in the SumoEnvironment code there's written "episode ends when sim_step >= max_steps", however inside _compute_dones the condition is only "self.sim_step > self.sim_max_time", missing the =.
Is this intended (and if yes, why > instead of >=?)?
If it's not intended, would you mind updating the code so that installing the library via pip will have the updated code?
Thanks.

LucasAlegre commented 1 year ago

Hi @Nyphet,

Thanks for noticing that! I fixed this and released version 1.4.1 with the updated code :)