Edouard Leurent

This is because for ParkingEnv is compatible with training with HER (Hindsight Experience Replay), which requires it to be ([see first warning](https://stable-baselines.readthedocs.io/en/master/modules/her.html#id1)) a [gym.GoalEnv](https://github.com/openai/gym/blob/3394e245727c1ae6851b504a50ba77c73cd4c65b/gym/core.py#L160), and GoalEnv environments use [Dict](https://github.com/Farama-Foundation/Gymnasium/blob/main/gymnasium/spaces/dict.py#L13) as...

not sure exactly how you defined `state` here, but it looks like it is a tuple containing `(obs, info)` (for instance, returned by `env.reset()`. so state[0] should get you the...

> If I wish to update the parameters of the observation space, should I add key-value pairs to config['observation'] instead of changing the formal parameter to config? Yes, that is...

Hi @Agathe48, Sorry about this, this has been fixed already in https://github.com/Farama-Foundation/HighwayEnv/commit/b0a4a847b70e60fc6e00f746ce325d7f869c3a9e (and yes you suggested the correct fix) But it hasn't made it into a release yet, I guess...

`v = Vehicle.make_on_lane(...)` aligns the vehicle heading with the lane direction, by default. you can just add the following line below to rotate the vehicles: ``` v = Vehicle.make_on_lane(...) v.heading...

Indeed, this reward plot is not very good, it's surprising that reward does not improve at all throughout training. It is true that the MlpPolicy is not best suited for...

> One problem is, I can't remove other vehicles, I mean even when I change "initial_vehicles_count" to 1 or 0, still there are other cars! One trick was make their...

Hi, For the highway-v0 run, I think that the problem is that the observation is configures with absolute coordinates (`absolute: True`) instead of relative (`absolute: False`). This means that the...

> By the way, I don't unsderstand the ego_spacing and "destination": "o1" and "scaling": 5.5 * 1.3 these parameter Could you please explain for me ? I would appreciate it...

> Hello! Can I control all the background vehicles myself, for example, by using a prediction model to output the trajectories of background vehicles, while the main vehicle uses IDM?...