Andreas Burger

Results 8 issues of Andreas Burger

### 🐛 Bug Using Procgen like in the [example from the docs website](https://stable-baselines3.readthedocs.io/en/master/guide/examples.html#sb3-and-procgenenv) results in: AssertionError: The algorithm only supports (, , , ) as action spaces but Discrete(15) was...

documentation
duplicate
good first issue
help wanted
check the checklist

How would one generate an action (output text) using PaLI? ## PaLI from `readme.md` ```Python import torch from x_transformers import ViTransformerWrapper, XTransformer, Encoder # PaLI composes of # 1. vision...

### Reproduce the error ``` TASK=homegrid_task; EXP_NAME=first_run; GPU_IDS=0; SEED=0 sh scripts/run_homegrid.sh $TASK $EXP_NAME $GPU_IDS $SEED ``` Encounters the error ``` ValueError: Non-hashable static arguments are not supported. An error occurred...

It's a very nieche problem, but tripped me over big time :') ### Issue For `model.eval()` , `z_pred` will not have tracked gradients (`z_pred.requires_gradient==False`). For custom torch.autograd this will lead...

### Reproduce error - flax 0.7.5 - jaxlib 0.4.21+cuda12.cudnn89 - Ubuntu 22.04 Running ```bash XLA_PYTHON_CLIENT_PREALLOCATE=false python train_finetuning_pixels.py --env_name=cheetah-run-v0 \ --start_training 5000 \ --max_steps 300000 \ --config=configs/rlpd_pixels_config.py \ --project_name=rlpd_vd4rl ``` I...

``` The 'sklearn' PyPI package is deprecated, use 'scikit-learn' rather than 'sklearn' for pip commands. Here is how to fix this error in the main use cases: - use 'pip...

It seems like the best fixed-point estimate `z_star = lowest_xest` is only returned when the indexed trajectory is empty. When one specifies `indexing`, they are not getting the best fixed-point...

Hi, Thanks again for this library! 1. Am I right in that `n_states` / `indexing` can be used to implement the _sparse fixed-point correction_ of [DEQ Optical Flow](https://arxiv.org/abs/2204.08442)? 2. If...