Edouard Leurent

you can configure the DQN agent with ``` dict(exploration= dict(temperature=1.0, final_temperature=0.1, tau=5000) ) ```

Hi, sorry I should really update the instruction. The analyze.py script is deprecated (I only used it to plot the rewards / episode length stats etc), you should use tensorboard...

> we have agents and trainer folders, what is each one for? The `agents` folder defines RL algorithms (an agent interact with an environment and updates its internal model), while...

Hi, thanks for the feedback! 1. You're right, maybe it's a bit confusing. My intent was to implement a lightweight RL library with many (unrelated) agents, and add my own...

1. the inputs is an array containing a set of per-vehicle features. For instance, I used position x, y (absolute or relative to ego vehicle position), velocity vx vy (absolute...

No worries at all, glad you found this helpful!

Hi, No, I have no idea why PyCharm would not stop at the breakpoint... I tried it and it worked fine  Are you running the program in debug mode...

> Do the columns of the attention matrix not correspond to the corresponding vehicles? Why do we need to assign attention values to vehicles based on their distances? They do!...

I think there can be two roles: 1. the decision may depend on the state of the vehicle, e.g. its current position, or its speed or heading. So the attention...

Please see e.g. [this colab](https://colab.research.google.com/github/eleurent/highway-env/blob/master/scripts/intersection_social_dqn.ipynb)