diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
new file mode 100644
index 0000000..eb05789
--- /dev/null
+++ b/CONTRIBUTING.md
@@ -0,0 +1,7 @@
+[Git Guide](https://di-engine-docs.readthedocs.io/en/latest/24_cooperation/git_guide.html)
+
+[GitHub Cooperation Guide](https://di-engine-docs.readthedocs.io/en/latest/24_cooperation/issue_pr.html)
+
+  - [Code Style](https://di-engine-docs.readthedocs.io/en/latest/21_code_style/index.html)
+  - [Unit Test](https://di-engine-docs.readthedocs.io/en/latest/22_test/index.html)
+  - [Code Review](https://di-engine-docs.readthedocs.io/en/latest/24_cooperation/issue_pr.html#pr-s-code-review)
\ No newline at end of file
diff --git a/README.md b/README.md
index 4b12396..f5a5cf7 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
     
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 
-English | [简体中文(Simplified Chinese)](https://github.com/opendilab/GenerativeRL_Preview/blob/main/README.zh.md)
+English | [简体中文(Simplified Chinese)](https://github.com/opendilab/GenerativeRL/blob/main/README.zh.md)
 
 **GenerativeRL**, short for Generative Reinforcement Learning, is a Python library for solving reinforcement learning (RL) problems using generative models, such as diffusion models and flow models. This library aims to provide a framework for combining the power of generative models with the decision-making capabilities of reinforcement learning algorithms.
 
@@ -62,8 +62,8 @@ pip install grl
 Or, if you want to install from source:
 
 ```bash
-git clone https://github.com/opendilab/GenerativeRL_Preview.git
-cd GenerativeRL_Preview
+git clone https://github.com/opendilab/GenerativeRL.git
+cd GenerativeRL
 pip install -e .
 ```
 
diff --git a/README.zh.md b/README.zh.md
index 903071c..337abec 100644
--- a/README.zh.md
+++ b/README.zh.md
@@ -2,7 +2,7 @@
     
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 
-[英语 (English)](https://github.com/opendilab/GenerativeRL_Preview/blob/main/README.md) | 简体中文
+[英语 (English)](https://github.com/opendilab/GenerativeRL/blob/main/README.md) | 简体中文
 
 **GenerativeRL** 是一个使用生成式模型解决强化学习问题的算法库，支持扩散模型和流模型等不同类型的生成式模型。这个库旨在提供一个框架，将生成式模型的能力与强化学习算法的决策能力相结合。
 
@@ -59,8 +59,8 @@ pip install grl
 或者，如果你想从源码安装：
 
 ```bash
-git clone https://github.com/opendilab/GenerativeRL_Preview.git
-cd GenerativeRL_Preview
+git clone https://github.com/opendilab/GenerativeRL.git
+cd GenerativeRL
 pip install -e .
 ```
 
diff --git a/docs/source/tutorials/installation/index.rst b/docs/source/tutorials/installation/index.rst
index ad818cd..b3be7df 100644
--- a/docs/source/tutorials/installation/index.rst
+++ b/docs/source/tutorials/installation/index.rst
@@ -17,4 +17,4 @@ If you want to try a preview of the latest features, you can install the latest
 
 .. code-block:: console
 
-   $ pip install git+https://github.com/opendilab/GenerativeRL_Preview.git
+   $ pip install git+https://github.com/opendilab/GenerativeRL.git
diff --git a/grl/algorithms/srpo.py b/grl/algorithms/srpo.py
index ba71306..f39c900 100644
--- a/grl/algorithms/srpo.py
+++ b/grl/algorithms/srpo.py
@@ -385,22 +385,11 @@ def policy(obs: np.ndarray) -> np.ndarray:
                 lr=config.parameter.behaviour_policy.learning_rate,
             )
 
-            # checkpoint = torch.load(
-            #     "/root/github/GenerativeRL_Preview/grl_pipelines/d4rl-halfcheetah-srpo/2024-04-17 06:22:21/checkpoint_diffusion_600000.pt"
-            # )
-            # self.model["SRPOPolicy"].sro.diffusion_model.model.load_state_dict(
-            #     checkpoint["diffusion_model"]
-            # )
-            # behaviour_model_optimizer.load_state_dict(
-            #     checkpoint["behaviour_model_optimizer"]
-            # )
-
             for train_diffusion_iter in track(
                 range(config.parameter.behaviour_policy.iterations),
                 description="Behaviour policy training",
             ):
                 data = next(data_generator)
-                # data["s"].shape  torch.Size([2048, 17])   data["a"].shape torch.Size([2048, 6])  data["r"].shape torch.Size([2048, 1])
                 behaviour_model_training_loss = self.model[
                     "SRPOPolicy"
                 ].behaviour_policy_loss(data["a"], data["s"])
@@ -408,10 +397,6 @@ def policy(obs: np.ndarray) -> np.ndarray:
                 behaviour_model_training_loss.backward()
                 behaviour_model_optimizer.step()
 
-                # if train_iter == 0 or (train_iter + 1) % config.parameter.evaluation.evaluation_interval == 0:
-                #     evaluation_results = evaluate(self.model["SRPOPolicy"], train_iter=train_iter)
-                #     wandb_run.log(data=evaluation_results, commit=False)
-
                 wandb_run.log(
                     data=dict(
                         train_diffusion_iter=train_diffusion_iter,
@@ -444,11 +429,6 @@ def policy(obs: np.ndarray) -> np.ndarray:
                 lr=config.parameter.critic.learning_rate,
             )
 
-            # checkpoint = torch.load(
-            #     "/root/github/GenerativeRL_Preview/grl_pipelines/d4rl-halfcheetah-srpo/2024-04-17 06:22:21/checkpoint_critic_600000.pt"
-            # )
-            # self.model["SRPOPolicy"].critic.q0.load_state_dict(checkpoint["q_model"])
-            # self.model["SRPOPolicy"].critic.vf.load_state_dict(checkpoint["v_model"])
             data_generator = get_train_data(
                 DataLoader(
                     self.dataset,