Jiayi Zhou
Jiayi Zhou
As one of the maintainers of Omnisafe, we are currently working on adding CVPO to our supported algorithm list. You can find more information about Omnisafe on our homepage at...
# Description **This PR is already complete in terms of implementation accuracy. We will merge it shortly after improving the code style and documentation.** ## Related Papers This Pull Request...
# Description **This PR is already complete in terms of implementation accuracy. We will merge it shortly after improving the code style and documentation.** Support Safe SLAC[1] algorithms for **[Safe...
### Required prerequisites - [X] I have searched the [Issue Tracker](https://github.com/PKU-Alignment/omnisafe/issues) and [Discussions](https://github.com/PKU-Alignment/omnisafe/discussions) that this hasn't already been reported. (+1 or comment there if it has.) - [X] Consider asking...
# Description Reformat & Update CHANGELOG for v0.6.0. ## Types of changes What types of changes does your code introduce? Put an `x` in all the boxes that apply: -...
### Required prerequisites - [X] I have searched the [Issue Tracker](https://github.com/PKU-Alignment/omnisafe/issues) and [Discussions](https://github.com/PKU-Alignment/omnisafe/discussions) that this hasn't already been reported. (+1 or comment there if it has.) - [X] Consider asking...
# Description This pull request is aimed at supporting environments with discrete action spaces and observation spaces. It has been implemented in the [Taxi-v3](https://gymnasium.farama.org/environments/toy_text/taxi/) and [CartPole-v1](https://gymnasium.farama.org/environments/classic_control/cart_pole/) environments in Gymnasium. Relevant...
# Description Update training template and support ta2t dpo. ## Types of changes What types of changes does your code introduce? Put an `x` in all the boxes that apply:...
### Required prerequisites - [X] I have read the documentation . - [X] I have searched the [Issue Tracker](https://github.com/PKU-Alignment/align-anything/issues) and [Discussions](https://github.com/PKU-Alignment/align-anything/discussions) that this hasn't already been reported. (+1 or comment...
# Description 🎉! We supported the SFT training of Qwen2.5-Omni within 1 hour! Here are the specific training screenshots👇  ## Test Please test your changes by running the following...