Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: OpenAI/Gym/MuJoCo-Walker2d-v3
     metrics:
     - type: mean_reward
-      value: 3696.61 +/- 1969.88
+      value: 3981.94 +/- 1332.9
       name: mean_reward
 ---
 
@@ -53,7 +53,8 @@ wget https://mujoco.org/download/mujoco210-linux-x86_64.tar.gz -O mujoco.tar.gz
 tar -xf mujoco.tar.gz -C ~/.mujoco
 echo "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mjpro210/bin:~/.mujoco/mujoco210/bin" >> ~/.bashrc
 export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mjpro210/bin:~/.mujoco/mujoco210/bin
-pip3 install DI-engine[common_env]
+pip3 install "cython<3"
+pip3 install DI-engine[common_env,video]
 
 ```
 </details>
@@ -76,9 +77,9 @@ import torch
 
 # Pull model from files which are git cloned from huggingface
 policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
-cfg = EasyDict(Config.file_to_dict("policy_config.py"))
+cfg = EasyDict(Config.file_to_dict("policy_config.py").cfg_dict)
 # Instantiate the agent
-agent = PPOF(env="Walker2d", exp_name="Walker2d-v3-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
+agent = PPOF(env_id="Walker2d-v3", exp_name="Walker2d-v3-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
 # Continue training
 agent.train(step=5000)
 # Render the new agent performance
@@ -104,7 +105,7 @@ from huggingface_ding import pull_model_from_hub
 # Pull model from Hugggingface hub
 policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/Walker2d-v3-PPO")
 # Instantiate the agent
-agent = PPOF(env="Walker2d", exp_name="Walker2d-v3-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
+agent = PPOF(env_id="Walker2d-v3", exp_name="Walker2d-v3-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
 # Continue training
 agent.train(step=5000)
 # Render the new agent performance
@@ -130,9 +131,9 @@ from ding.bonus import PPOF
 from huggingface_ding import push_model_to_hub
 
 # Instantiate the agent
-agent = PPOF(env="Walker2d", exp_name="Walker2d-v3-PPO")
+agent = PPOF(env_id="Walker2d-v3", exp_name="Walker2d-v3-PPO")
 # Train the agent
-return_ = agent.train(step=int(10000000), collector_env_num=4, evaluator_env_num=4, debug=False)
+return_ = agent.train(step=int(5000000))
 # Push model to huggingface hub
 push_model_to_hub(
     agent=agent.best,
@@ -164,12 +165,14 @@ wget https://mujoco.org/download/mujoco210-linux-x86_64.tar.gz -O mujoco.tar.gz
 tar -xf mujoco.tar.gz -C ~/.mujoco
 echo "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mjpro210/bin:~/.mujoco/mujoco210/bin" >> ~/.bashrc
 export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mjpro210/bin:~/.mujoco/mujoco210/bin
-pip3 install DI-engine[common_env]
+pip3 install "cython<3"
+pip3 install DI-engine[common_env,video]
 ''',
     usage_file_by_git_clone="./ppo/walker2d_ppo_deploy.py",
     usage_file_by_huggingface_ding="./ppo/walker2d_ppo_download.py",
     train_file="./ppo/walker2d_ppo.py",
-    repo_id="OpenDILabCommunity/walker2d-v3-PPO"
+    repo_id="OpenDILabCommunity/Walker2d-v3-PPO",
+    create_repo=False
 )
 
 ```
@@ -204,7 +207,9 @@ exp_config = {
     'unroll_len': 1,
     'deterministic_eval': True,
     'model': {},
-    'cfg_type': 'PPOFPolicyDict'
+    'cfg_type': 'PPOFPolicyDict',
+    'env_id': 'Walker2d-v3',
+    'exp_name': 'Walker2d-v3-PPO'
 }
 
 ```
@@ -212,23 +217,23 @@ exp_config = {
 
 **Training Procedure** 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/ruoyugao/Walker2d-v3-PPO)
+- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/Walker2d-v3-PPO)
 
 ## Model Information
 <!-- Provide the basic links for the model. -->
 - **Github Repository:** [repo link](https://github.com/opendilab/DI-engine)
 - **Doc**: [DI-engine-docs Algorithm link](https://di-engine-docs.readthedocs.io/en/latest/12_policies/ppo.html)
-- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/walker2d-v3-PPO/blob/main/policy_config.py)
-- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/walker2d-v3-PPO/blob/main/replay.mp4)
+- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-PPO/blob/main/policy_config.py)
+- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-PPO/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
 - **Parameters total size:** 385.85 KB
-- **Last Update Date:** 2023-06-14
+- **Last Update Date:** 2023-09-25
 
 ## Environments
 <!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
 - **Benchmark:** OpenAI/Gym/MuJoCo
 - **Task:** Walker2d-v3
 - **Gym version:** 0.25.1
-- **DI-engine version:** v0.4.8
-- **PyTorch version:** 1.7.1
+- **DI-engine version:** v0.4.9
+- **PyTorch version:** 2.0.1+cu117
 - **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/mujoco.html)