-
## Describe the bug
I'm unable to use DQN on the latest commit.
## To Reproduce
```bash
conda create -n torchrl python
conda activate torchrl
pip install torch
git clone https://github.com/py…
-
CARLA version: 0.9.14
Platform/OS: Windows 10
I am using PyTorch and DQN to implement an autonomous vehicle, and while running the learning program, CarlaUE4 sometimes crashes seemingly at random …
-
### 🐛 Bug
VecExtractDictObs Wrapper currently does not update the ``terminal_observation`` entry in the info returned by VecEnv.
This causes an exception when storing into a buffer, since the observ…
-
### 🐛 Bug
After install tqdm, model.learn with profress_bar occur ImportError
"model.learn(total_timesteps=int(200), progress_bar=True)"
### To Reproduce
```python
import gym
from stable_base…
-
### Bug description
The error `TPUs do not currently support IterableDataset objects, the dataset must implement `__len__`. HINT: You can mock the length on your dataset to bypass this error.` is r…
-
I am following multi stock notebook. When about to train the first model I got this error message:
Model 1: A2C
agent = DRLAgent(env = env_train)
model_a2c = agent.get_model("a2c")
{'n_steps': 5…
-
## ❓ Questions and Help
I am using Anaconda in Windows and tried following the installation from source instructions by running
`git clone https://github.com/facebookresearch/mmf.git`
`cd mmf`
`p…
-
### 🐛 Bug
I'm using the Proximal Policy Optimization (PPO) algorithm to train an agent in an OpenAI gym environment for trading. After training the agent and saving it, I reload it and run simulati…
-
Hello, when I am trying to run a tutorial script, e.g. the your_first_program example, I always encounter this AttributeError during the imports:
AttributeError: module 'torch.distributed.rpc' has …
-
### 🐛 Bug
When using an image as state with format `HxWxC` in combination with the `normalize=True` hyperparameter, the training will crash. This is probably because the `VecNormalize` is applied bef…