feat: support safe slac

[Gaiejj]

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 Vision tasks in Safety-Gymnasium

[1]: Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation

Example Demo

safe_slac.mp4

Experiment and Performance

• SafetyCarGoal1Vision-v1
  
• SafetyPointButton1Vision-v1
  
• SafetyPointGoal1Vision-v1
  
• SafetyPointGoal2Vision-v1
  

Motivation and Context

Vision-based safety tasks are of great significance for the safe exploration of agents. The interface for Safe Vision will promote the development of vision-based SafeRL algorithms.

Types of changes

What types of changes does your code introduce? Put an x in all the boxes that apply:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds core functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation (update in the documentation)

Checklist

Go over all the following points, and put an x in all the boxes that apply.
If you are unsure about any of these, don't hesitate to ask. We are here to help!

• I have read the CONTRIBUTION guide. (required)
• My change requires a change to the documentation.
• I have updated the tests accordingly. (required for a bug fix or a new feature)
• I have updated the documentation accordingly.
• I have reformatted the code using make format. (required)
• I have checked the code using make lint. (required)
• I have ensured make test pass. (required)

[codecov]

Codecov Report

Attention: Patch coverage is 27.43056% with 418 lines in your changes are missing coverage. Please review.

Project coverage is 91.63%. Comparing base (93d4975) to head (9fd5fd7).
Report is 1 commits behind head on main.

❗ Current head 9fd5fd7 differs from pull request most recent head 277b6e1. Consider uploading reports for the commit 277b6e1 to get more accurate results

Files	Patch %	Lines
omnisafe/common/latent.py	20.92%	121 Missing ⚠️
omnisafe/algorithms/off_policy/safe_slac.py	19.67%	98 Missing ⚠️
omnisafe/adapter/offpolicy_latent_adapter.py	24.39%	93 Missing ⚠️
omnisafe/common/buffer/offpolicy_buffer.py	33.33%	26 Missing ⚠️
omnisafe/utils/tools.py	35.00%	26 Missing ⚠️
omnisafe/envs/safety_gymnasium_vision_env.py	46.67%	24 Missing ⚠️
omnisafe/utils/model.py	40.74%	16 Missing ⚠️
omnisafe/common/buffer/base.py	39.13%	14 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #324      +/-   ##
==========================================
- Coverage   96.83%   91.63%   -5.21%     
==========================================
  Files         138      142       +4     
  Lines        7071     7643     +572     
==========================================
+ Hits         6847     7003     +156     
- Misses        224      640     +416     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.