-
Hi! I have several questions/requests regarding value learning https://github.com/deepmind/rlax/blob/master/rlax/_src/value_learning.py
1. If I want to use the `_quantile_regression_loss` without …
-
Error when running `pip install dm-acme[acme]`, using python `3.9.10` and pip `22.0.3`
```
Collecting dm-acme[jax]
Using cached dm-acme-0.2.3.tar.gz (297 kB)
Preparing metadata (setup.py) .…
akbir updated
2 years ago
-
rlax gives the following error when I try to install:
Collecting jaxlib>=0.1.37 (from rlax==0.0.1)
Could not find a version that satisfies the requirement jaxlib>=0.1.37 (from rlax==0.0.1) (from v…
renos updated
3 years ago
-
`truncated_generalized_advantage_estimation` should have the `stop_target_gradients` defaulted to `True`
https://github.com/deepmind/rlax/blob/383f93bc8b33c3d1bc28f15e1e07fc5104c790ea/rlax/_src/mul…
-
Hi,
Thanks for releasing the source code, it helps a lot.
I'm currently working on a similar project, but I'm wondering if there is any way to display the current values of each tensor with rlax d…
-
I would like to propose an API enhancement that allow the use of chex.Dimensions inside function annotations. If there is interest I'd like to contribute. Example below:
```
dims = chex.Dimensions(B…
-
The users should be able to run the framework following ONLY the installation guide.
I think easiest to use via `conda`.
-
Hi There,
Thanks for open-sourcing!
The dependencies are really hard to reconstruct as it seems that Jax is changing its API quite heavily between minor releases.
How to reproduce the bug: Foll…
-
Hi,
I have some silly questions about updating the agent. I know the general framework of training is as follow:
```
while True:
# Make an initial observation.
step = environment.reset()
a…
-
## Paste the link of the GitHub organisation below and submit
https://github.com/deepmind