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: 5115.65 +/- 19.18
+      value: 5296.43 +/- 19.68
       name: mean_reward
 ---
 
@@ -53,6 +53,7 @@ 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 "cython<3"
 pip3 install DI-engine[common_env]
 
 ```
@@ -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 = SACAgent(env="Walker2d", exp_name="Walker2d-v3-SAC", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
+agent = SACAgent(env_id="Walker2d-v3", exp_name="Walker2d-v3-SAC", 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-SAC")
 # Instantiate the agent
-agent = SACAgent(env="Walker2d", exp_name="Walker2d-v3-SAC", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
+agent = SACAgent(env_id="Walker2d-v3", exp_name="Walker2d-v3-SAC", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
 # Continue training
 agent.train(step=5000)
 # Render the new agent performance
@@ -126,11 +127,11 @@ python3 -u train.py
 ```
 **train.py**
 ```python
-from ding.bonus.sac import SACAgent
+from ding.bonus import SACAgent
 from huggingface_ding import push_model_to_hub
 
 # Instantiate the agent
-agent = SACAgent(env="Walker2d", exp_name="Walker2d-v3-SAC")
+agent = SACAgent(env_id="Walker2d-v3", exp_name="Walker2d-v3-SAC")
 # Train the agent
 return_ = agent.train(step=int(5000000))
 # Push model to huggingface hub
@@ -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 "cython<3"
 pip3 install DI-engine[common_env]
 ''',
     usage_file_by_git_clone="./sac/walker2d_sac_deploy.py",
     usage_file_by_huggingface_ding="./sac/walker2d_sac_download.py",
     train_file="./sac/walker2d_sac.py",
-    repo_id="OpenDILabCommunity/Walker2d-v3-SAC"
+    repo_id="OpenDILabCommunity/Walker2d-v3-SAC",
+    create_repo=False
 )
 
 ```
@@ -194,16 +197,11 @@ exp_config = {
             'cfg_type': 'BaseEnvManagerDict'
         },
         'stop_value': 6000,
+        'n_evaluator_episode': 8,
         'env_id': 'Walker2d-v3',
-        'norm_obs': {
-            'use_norm': False
-        },
-        'norm_reward': {
-            'use_norm': False
-        },
         'collector_env_num': 1,
         'evaluator_env_num': 8,
-        'n_evaluator_episode': 8
+        'env_wrapper': 'mujoco_default'
     },
     'policy': {
         'model': {
@@ -257,9 +255,10 @@ exp_config = {
                     'render_freq': -1,
                     'mode': 'train_iter'
                 },
+                'figure_path': None,
                 'cfg_type': 'InteractionSerialEvaluatorDict',
-                'n_episode': 8,
-                'stop_value': 6000
+                'stop_value': 6000,
+                'n_episode': 8
             }
         },
         'other': {
@@ -297,7 +296,7 @@ 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/zhangpaipai/Walker2d-v3-SAC)
+- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/Walker2d-v3-SAC)
 
 ## Model Information
 <!-- Provide the basic links for the model. -->
@@ -306,14 +305,14 @@ exp_config = {
 - **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-SAC/blob/main/policy_config.py)
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-SAC/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
-- **Parameters total size:** 851.05 KB
-- **Last Update Date:** 2023-04-18
+- **Parameters total size:** 1702.11 KB
+- **Last Update Date:** 2023-09-23
 
 ## 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:** v0.4.7
-- **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)