-
I made some toy benchmark by creating 16 environments for both `SubprocVecEnv` and `DummyVecEnv`. And collect 1000 time steps by firstly reset the environment and feed random action sampled from actio…
-
With [PEP560](https://www.python.org/dev/peps/pep-0560/) we could now try to have a better annotations experience for Pint. Briefly, my proposal would be to do something like this
```python
class …
-
- [x] I have searched the [issues](https://github.com/sdispater/poetry/issues) of this repo and believe that this is not a duplicate.
## Issue
It would be awesome if Poetry had a command…
-
## Describe the bug
Appending the `TensorDictPrimer` transform created from `LSTMModule.make_tensordict_primer` triggers dimension error.
## To Reproduce
```python
import torchrl
from torch…
-
Hi, I was just getting started with this amazing d3rlpy library, and wanted to train a very simple policy using DQN on the cartpole environment. But I'm not sure why the loss and TD errors (both valid…
-
Hi,
First of all, thank you all for your work on this project — it's proven fantastic for understanding memory pressure and experimenting with training!
I noticed, however, that the title and le…
-
Had a conversation with @jkterry1 on https://github.com/openai/gym/issues/2366, and it appears brax would also be a great alternative for the mujoco envs replacement.
To help with this transition.…
-
playing with https://github.com/LinkedEarth/PaleoBooks/blob/master/notebooks/EDC_demo.ipynb
`sep="/s+" `
seems to load the txt correctly
-
### What is the problem?
When running SAC on Pendulum-v0 with gpu and single or multiple workers, rllib suffers from a memory leak independently of the framework used (tf or torch). The attached log …
-
IMPALA (TensorFlow) crashes with `IndexError: index 138 is out of bounds for axis 0 with size 132` if using an RNN and `num_sgd_iter > 1`.
config:
```
num_sgd_iter: 2
model:
- use_lstm: …