rl

rl copied to clipboard

```python a = MultiCategorical([[3, 2],[1,4]]) a.to_one_hot_spec() ``` ```bash Traceback (most recent call last): File "/opt/homebrew/Caskroom/miniforge/base/envs/torchrl-3.11/lib/python3.11/site-packages/IPython/core/interactiveshell.py", line 3577, in run_code exec(code_obj, self.user_global_ns, self.user_ns) File "", line 1, in a.to_one_hot_spec() File "/Users/Matteo/PycharmProjects/torchrl/torchrl/data/tensor_specs.py",...

matteobettini

### Discussed in https://github.com/pytorch/rl/discussions/2341 Originally posted by **hesic73** July 31, 2024 I have a question about the order of keys returned by `CompositeSpec.keys(include_nested=True, leaves_only=False)`. Is there any guarantee on the...

vmoens

## Describe the bug Similar issue as [here](https://github.com/pytorch/rl/issues/2439). The `MaskedCategorical` distribution is missing the `mode` and `deterministic_sample` properties. ## Reason and Possible fixes The `MaskedCategorical` distribution should define the following...

MorganeAyle

[BUG] GAE parameters (gamma, lmbda) seemed to get changed by ClipPPOLoss, advantage module does not calculate loss_critic

1

### Environment OS: Windows 11 Python : CPython 3.10.14 Torchrl Version : 0.5.0 PyTorch Version : 2.4.1+cu124 Gym Environment: A custom subclass of EnvBase (from torchrl.envs) The project I'm working...

therealjoker4u