Merge pull request #2 from zmsn-2077/first-order

refactor: change architecture of omnisafe (PKU-MARL#121)

omnisafe/algorithms/on_policy/README.md

@@ -11,15 +11,10 @@ Supported algorithms are listed below:
 **First-Order**
 
 - **[NIPS 1999]** [Policy Gradient(PG)](https://papers.nips.cc/paper/1999/file/464d828b85b0bed98e80ade0a5c43b0f-Paper.pdf)
-
 - [Proximal Policy Optimization (PPO)](https://arxiv.org/pdf/1707.06347.pdf)
-
 - [The Lagrange version of PPO (PPO-Lag)](https://cdn.openai.com/safexp-short.pdf)
-
 - **[IJCAI 2022]** [Penalized Proximal Policy Optimization for Safe Reinforcement Learning(P3O)]( https://arxiv.org/pdf/2205.11814.pdf)
-
 - **[NeurIPS 2020]** [First Order Constrained Optimization in Policy Space (FOCOPS)](https://arxiv.org/abs/2002.06506)
-
 - **[NeurIPS 2022]**  [Constrained Update Projection Approach to Safe Policy Optimization (CUP)](https://arxiv.org/abs/2209.07089)
 
 **Second-Order**