feat(simmer): update config, benchmark results and code style

[Gaiejj]

Description

• feat: update simmer configs
• feat: update simmer results
• fix: fix simmer adapter
• style: update pre-commit version

Similar to #274, we summarized our insights as the following:

• obs_normalize=True is critical for TRPOSimmerPID but not so work for PPOSimmerPID. We observed that obs_normalize=True is inferior in Goal and Circle tasks for PPOSimmerPID.
• The previous PPOSimmerPID and TRPOSimmerPID algorithms exhibited excessive conservatism in Goal tasks, which is highly related to the algo_cfgs:unsafe_reward parameter. We explored values of 0.0, -0.1, -0.2, and -0.5 for this parameter and found that its value significantly affects the algorithm's performance. Lower values of algo_cfgs:unsafe_reward tend to result in more conservative strategies. Taking into account the trade-off between reward and cost, we have temporarily selected -0.2 as a comprehensive value.
• algo_cfgs:saute_gamma parameter has a strong influence on the stability of the algorithm. In the case of Goal tasks, we have found that a value of 0.9999 performs better than 0.999. This suggests that a higher algo_cfgs:saute_gamma value improves the stability of the algorithm for Goal tasks.

Detailedly, we fine-tune the performance of PPOSimmer and TRPOSimmer in

• SafetyPointGoal1-v0
  
• SafetyCarGoal1-v0
  
• SafetyPointCircle1-v0
  
• SafetyCarCircle1-v0
  
• SafetyPointGoal2-v0
  
• SafetyCarGoal2-v0
  
• SafetyPointCircle2-v0
  
• SafetyCarCircle2-v0
  

This Pull Request also resolves some code style issue.

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

Merging #280 (608173c) into main (c575fd5) will not change coverage.
The diff coverage is 100.00%.

❗ Current head 608173c differs from pull request most recent head 9ad1ff2. Consider uploading reports for the commit 9ad1ff2 to get more accurate results

@@           Coverage Diff           @@
##             main     #280   +/-   ##
=======================================
  Coverage   97.01%   97.01%           
=======================================
  Files         138      138           
  Lines        6991     6991           
=======================================
  Hits         6782     6782           
  Misses        209      209           

Files	Coverage Δ
omnisafe/adapter/simmer_adapter.py	100.00% <100.00%> (ø)
omnisafe/algorithms/model_based/base/ensemble.py	94.86% <100.00%> (ø)
omnisafe/algorithms/offline/vae_bc.py	100.00% <100.00%> (ø)
omnisafe/common/normalizer.py	98.57% <100.00%> (-0.02%)	⬇️
omnisafe/models/actor/actor_builder.py	96.30% <100.00%> (+0.14%)	⬆️
omnisafe/models/actor/gaussian_sac_actor.py	97.83% <ø> (ø)
omnisafe/models/actor_critic/actor_critic.py	100.00% <100.00%> (ø)
omnisafe/models/actor_critic/actor_q_critic.py	97.73% <100.00%> (-0.05%)	⬇️

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more