pytorch-PPUU
pytorch-PPUU copied to clipboard
Atcold
Code for Prediction and Planning Under Uncertainty (PPUU)
```bash python play_maps.py -map i80 ``` ```python Traceback (most recent call last): File "play_maps.py", line 81, in observation, reward, done, info = env.step(action) File "/anaconda3/envs/PPUU/lib/python3.8/site-packages/gym/wrappers/order_enforcing.py", line 37, in step return...
Enable code base to incorporate [highD dataset](https://www.highd-dataset.com/) into project pipeline New scripts and files: - `map_highD.py`: Main script that creates environment and car classes for highD dataset - `scripts/run_generate_data_highD.sh` -...
In order to be able to address each and every type of failure, we need to implement a visualisation tool, which allows us to shed some light on WTF is...
A huge overhead exists right now because we draw the entire road segment, not only the surroundings of the car we are driving.
Right now, the evaluation happens sequentially, but should be parallel. Need to implement similarly to the link below: [`run.py`](https://github.com/Atcold/baselines/blame/traffic/baselines/run.py)
`/home/atcold/Work/GitHub/pytorch-Traffic-Simulator/utils.py:72: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).`