Problems with Stable Version and Nightly version

[AdrianPrados]

Good morning, my name is Adrián Prados, PhD student at the University of Carlos III. I am currently working on imitation learning and I would like to use your framework to work with your datasets as well as to implement my own Imitation Learning algorithms. I have tried to install both versions, the stable and the nigthl version and both have given me problems. For the installation I have been following your steps . There are problems in the initialisations of the different simulators, there are repeated functions that contradict each other (the init() function is defined several times in the same class generating problems) and also the function calls have changed with respect to the documentation. I was wondering if this is something temporary or if there is some kind of problem or bug, since I can start working with at least the stable version.

Additionally I would also like to comment that the documentation is quite incomplete and there is not much information on how to start working in more depth with this framework. I don't know if it's still under development or if it's a problem between versions or a bug.

In any case I would like to know if there is any way to solve it to be able to start working with this framework as it seems interesting, useful and relatively quick to use.

[AdrianPrados]

Hello, i write again to provide some examples and probes that the "stable version" does not work properly. I have try to use the code provides in the Franka simulator and 2 different errors appears. The first one is: As can be seen, there is an error about the gym attribute. The second error is: In this case, the rofucn has no attribute oslab. Please confirm if there is any issue with the installation of the "stable version". I have the same errors using the nihgtly version.

Thank you very much for yous help.

[Skylark0924]

Thank you very much! Since this repo is updated too frequently, there often exist some problems. Especially since we have to prepare ICRA papers recently, we have added a lot of functions to the main branch. I'll refactor and test the entire repo in the near future (next week). I'll let you know in this issue if the test is complete. Thanks again for the advice!

[AdrianPrados]

Thank you very much and I look forward to your changes. Currently, in order to create my own code, I am making the necessary modifications to your code on my computer.

I would like to additionally raise a question about task_params. I have created some for the process of creating the representation model, but when I want to make a call to representation.create() even though I add some new task_params, the results returned (traj_l and traj_r) are the same as those obtained with the initial task_params. I was wondering if there is also some kind of bug or I'm doing some step incorrectly.

Attached is an image where I have modified the start and end values of the left and right vias and I have left vias 1 and 2 the same. I have also tried to modify the vias but the same thing happens.

Thank you very much for your help.

[Skylark0924]

For the Reinforcement Learning part

All RofuncRL examples (suffix with _RofuncRL.py) under examples/learning_rl are available now. Please feel free to try and find out whether there is any issue. Thanks!

You can run these examples like:

python examples/example_Ant_RofuncRL.py --inference

More detailed usages can be found in the example gallery of RL part.

[Skylark0924]

Hello, i write again to provide some examples and probes that the "stable version" does not work properly. I have try to use the code provides in the Franka simulator and 2 different errors appears. The first one is: As can be seen, there is an error about the gym attribute. The second error is: In this case, the rofucn has no attribute oslab. Please confirm if there is any issue with the installation of the "stable version". I have the same errors using the nihgtly version.

Thank you very much for yous help.

For the simulation part Bugs were fixed by 🎮 Fix bugs

• please refer to example_robot_show.py to test the interactive mode
• please refer to example_franka_track_traj.py to test the traj tracking with Franka robot
• please refer to example_curi_track_traj.py to test the traj tracking with CURI robot