Jiayi Zhou

Thanks for your early reply, which is surely insightful. I try to run your implementation of ``CVPO`` in ``SafetyPointGoal1-v0`` and ``SafetyCarGoal1-v0`` in https://github.com/OmniSafeAI/safety-gymnasium . I will also implement ``CVPO`` in...

@umfundii Hello, here is the complete reproduction process: 1. Create a new conda environment. ```bash conda create -n cbf python==3.8 ``` 2. Install OmniSafe (this is because the CBF-based method...

We are currently in the iterative development process and expect to be ready within a week. Thank you very much for your support.

@umfundii Thank you very much for pointing that out! It greatly helps us improve the robustness and usability of the code in this PR. - We have added the functionality...

@jyao97 Hello, We have released environment customization tutorials. Please feel free to use it and report any more problems. https://github.com/PKU-Alignment/omnisafe/tree/main/tutorials

We will update the code library for the customized environment interface to PyPI recently. Before that, please choose to install from the source code when running the tutorial.

@umfundii Thank you again for your detailed observations and feedback! 1. Based on the latest code, we conducted extensive repeated experiments on 5 random seeds and found that the results...

@umfundii Hello! We have refactored the CBF code. Specifically, we decoupled the `solver` and `dynamics_model` to facilitate user customization for specific environments. We have also completed the documentation for this...

We have released the new version of our project to PyPI, i.e., `0.5.0`. However, if you running `pip install omnisafe` directly in colab, a warning will be raised: ```bash WARNING:...

Yes, the location where the experimental results are saved is ``examples/runs/CPO-{Custom0-v0}/seed-000-2024-02-29-23-33-21``. In fact, both methods of evaluating trained policies are fine. The ``omnisafe eval`` command provides more extensive command line...