Toni-SM

Hi, Following this too!

The idea about generalization for other agents looks good... Whenever it is possible to avoid modifying the arguments of the agent constructors well. But there are cases where it is...

By the way, the current TRPO implementation iterates through learning epochs for both, the policy and the value... When it should be only for value ( the optimization of the...

Hi @akux2021 Yes, skrl allows using complex spaces like `gym.spaces.Dict`. The observations are automatically converted to flatten tensors to store them in memory. The flattened tensor is forward to the...

Hi, A solution for getting the robot state while moving, for all supported motions types can be found in the [pull request](https://github.com/pantor/frankx/pull/44) https://github.com/pantor/frankx/pull/44 With this modification it is possible to...

Hi @kyuwon416 **skrl**-v1.0.0 introduced some breaking changes regarding to model instantiators. Current Isaac Orbit version only works for skrl

Hi @MiguelASTavares Make sure you are compiling the [robot-state](https://github.com/Toni-SM/frankx/tree/robot-state) branch and not the `main` branch. The `robot-state` branch has the modified code for getting the robot state while moving and...

Hi @MiguelASTavares Are you importing frankx? ```python import frankx ``` And, the compiled files provided above are just a compilation of the branch...

Hi @MiguelASTavares This pull request just stores the current RobotState on each motion update and modifies the API to return the RobotState when the original methods are called with the...

Hi @bwunaver Can you please check that all changes defined in this pull request are for all related [files](https://github.com/pantor/frankx/pull/44/files )?