Edouard Leurent

There has been some recent changes in the last gym versions broke a few things, and repos like this one or SB3 are still adjusting. However I got it to...

Hello Bernicorn, I do not understand the purpose of this PR, since the IDM longitudinal controller is already implemented in https://github.com/eleurent/highway-env/blob/3ef36a0fb17f91769ecac9581206bd51cce41108/highway_env/vehicle/behavior.py#L12 which is a subclass of `ControlledVehicle`.

Right, okay. However, your proposed change results in duplicated code, which is not ideal. I think that a better solution would be to propose a new ActionType, which uses the...

No @dependabot, this version 2.4.1 is (currently) required by https://github.com/jupyterlab/jupyterlab_pygments, which itself is needed for the use of https://github.com/jupyter/jupyter-sphinx in the documentation

Keep up the good work! :)

By the way, this can now be achieved with action configurations, see [the documentation](https://highway-env.readthedocs.io/en/latest/actions/index.html)

This is now implemented in https://github.com/eleurent/highway-env/blob/dc02c0b8858cd061a92b2f2887b46bd5b8fc5b88/highway_env/envs/intersection_env.py#L275, closing this.

Yes, that is because by default, the agent rewards are aggregated in a single signal with a sum, in a cooperative fashion. See eg https://github.com/eleurent/highway-env/blob/049888adea0537b8e2d1d52aa0ae5b5722610629/highway_env/envs/intersection_env.py#L68 This was done because it...

Hi @TheNeeloy, I think you have a very good understanding of what's going on, but here's a a small clarification to make sure we are on the same page. >...

Actually, as I'm reading this code again, it seems that it already does what we want: do a lane change if it is safe and if it goes in the...