Luca Anzalone

@Ezharjan Try to comment [this](https://github.com/Luca96/carla-driving-rl-agent/blob/master/main.py#L3) line, and try again. In the log you should now see that tensorflow is allocating memory for your GPU, if not you may have a...

Hi, the warning about the CUDA libraries is related to your installation of Nvidia `cuda`, `cudnn`, etc. Anyway this is just a warning not an error, and means that if...

Hi, I trained and run the agent on a workstation with 18C/36T CPU, 128 GB of RAM, and an RTX 6000 with 24GB VRAM. I think that a CPU with...

Hi, you can find the description of the observation space [here](https://github.com/Luca96/carla-driving-rl-agent/blob/master/core/carla_env.py). In particular: * `image`: is a concatenation of tree RGB camera images, along width axis. * [road](https://github.com/Luca96/carla-driving-rl-agent/blob/master/core/carla_env.py#L335-L351): see the...

Hi, sorry for the late response. What issues are your facing, and what you would like to research? I anticipate that the agent is specifically designed to work only with...

ok, so: 1. If you just need to collect data, e.g. for imitation learning, you can use the [CARLACollectWrapper](https://github.com/Luca96/carla-driving-rl-agent/blob/master/rl/environments/carla/environment.py#L667) that wraps an instantiated CARLA environment, and by default saves the...

Hi @DeLeonOscar, maybe you're installing the CARLA package in your main python directory and *not* in a virtualenv (if using any), or vice-versa. Anyway, I'm reading [here](https://carla.readthedocs.io/en/0.9.14/start_quickstart/) that with newer...

Hi, thanks for the compliment. Yeah, I know FPS is an issue. With the hardware I had (i9 + RTX 6000), I was able to achieve about 10-15 fps, which...

Hi, apology for the late response.. In principle it should be possibile but in practice is useless since the agent makes sequential decisions: it has to first wait for the...

Hi, I guess the error is due to the newer versions of `gym` to have adopted a new API, and so old things have broken... Try to install version 0.22...