-
Hi there,
Thanks for your contribution and your package update!
I would like to ask if I am using the pre-trained model and I would like to not train it for more timestep, how would I set the …
-
### Proposal
Support Cupy as an alternative backend while using vectorized environment.
Give me some insight of the performance discripency comparing with my own VecEnv.
### Motivation
Approxima…
-
I am looking to use Brax Reacher task as an alternative to Mujoco Reacher for some RL tasks, but I have some concerns:
In [Mujoco Reacher task ](https://www.gymlibrary.dev/environments/mujoco/reacher…
-
```
With the changes from 9.5 to 9.6, Sequel Pro is nearly flawless, and absolutely
awesome. It is by far
my program of choice, but sometimes I have to deal with other RDBMSs, and I
have to use s…
-
**Important Note: We do not do technical support, nor consulting** and don't answer personal questions per email.
Please post your question on the [RL Discord](https://discord.com/invite/xhfNqQv), [R…
-
Hi,
I loaded the XML model in such way,
```
mj_model = mujoco.MjModel.from_xml_path(model_path)
sys = mjcf.load_model(mj_model)
```
then got the error described in title once this line code wa…
-
Hi, I am trying to run my environment using MJX, and everything works perfectly fine when I use PPO. When using PPO I can easily go to over 8000 environments, with batch size over 1000 without any mem…
-
Hi,
I'm looking for some help with MJX.
The function `pipeline_step()` ('mjx' backend) inside of `step()` of gymnasium env framework doesn't work well and returns a new data (pipeline_state) con…
-
Hi,
I was considering using acrobot for some experiments in Brax. What prompted its removal from the repo back in March 30th's commits?
Thanks!
-
I was wondering how you would extend an existing algorithm, let's say es to allow for a recurrent neural network instead of a feedforward one. You would need to change `make_policy_network` to replace…