Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: OpenAI/Gym/MuJoCo-HalfCheetah-v3
     metrics:
     - type: mean_reward
-      value: 12055.93 +/- 76.91
+      value: 11902.91 +/- 87.23
       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]
 
 ```
@@ -69,21 +70,7 @@ python3 -u run.py
 ```
 **run.py**
 ```python
-from ding.bonus import SACAgent
-from ding.config import Config
-from easydict import EasyDict
-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"))
-# Instantiate the agent
-agent = SACAgent(env="HalfCheetah", exp_name="HalfCheetah-v3-SAC", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
-# Continue training
-agent.train(step=5000)
-# Render the new agent performance
-agent.deploy(enable_save_replay=True)
-
+# [More Information Needed]
 ```
 </details>
 
@@ -98,18 +85,7 @@ python3 -u run.py
 ```
 **run.py**
 ```python
-from ding.bonus import SACAgent
-from huggingface_ding import pull_model_from_hub
-
-# Pull model from Hugggingface hub
-policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/HalfCheetah-v3-SAC")
-# Instantiate the agent
-agent = SACAgent(env="HalfCheetah", exp_name="HalfCheetah-v3-SAC", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
-# Continue training
-agent.train(step=5000)
-# Render the new agent performance
-agent.deploy(enable_save_replay=True)
-
+# [More Information Needed]
 ```
 </details>
 
@@ -126,52 +102,7 @@ python3 -u train.py
 ```
 **train.py**
 ```python
-from ding.bonus.sac import SACAgent
-from huggingface_ding import push_model_to_hub
-
-# Instantiate the agent
-agent = SACAgent(env="HalfCheetah", exp_name="HalfCheetah-v3-SAC")
-# Train the agent
-return_ = agent.train(step=int(5000000))
-# Push model to huggingface hub
-push_model_to_hub(
-    agent=agent.best,
-    env_name="OpenAI/Gym/MuJoCo",
-    task_name="HalfCheetah-v3",
-    algo_name="SAC",
-    wandb_url=return_.wandb_url,
-    github_repo_url="https://github.com/opendilab/DI-engine",
-    github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/sac.html",
-    github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/mujoco.html",
-    installation_guide='''
-sudo apt update -y \
-    && sudo apt install -y \
-    build-essential \
-    libgl1-mesa-dev \
-    libgl1-mesa-glx \
-    libglew-dev \
-    libosmesa6-dev \
-    libglfw3 \
-    libglfw3-dev \
-    libsdl2-dev \
-    libsdl2-image-dev \
-    libglm-dev \
-    libfreetype6-dev \
-    patchelf
-
-mkdir -p ~/.mujoco
-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]
-''',
-    usage_file_by_git_clone="./sac/halfcheetah_sac_deploy.py",
-    usage_file_by_huggingface_ding="./sac/halfcheetah_sac_download.py",
-    train_file="./sac/halfcheetah_sac.py",
-    repo_id="OpenDILabCommunity/HalfCheetah-v3-SAC"
-)
-
+# [More Information Needed]
 ```
 </details>
 
@@ -194,16 +125,11 @@ exp_config = {
             'cfg_type': 'BaseEnvManagerDict'
         },
         'stop_value': 12000,
+        'n_evaluator_episode': 8,
         'env_id': 'HalfCheetah-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 +183,10 @@ exp_config = {
                     'render_freq': -1,
                     'mode': 'train_iter'
                 },
+                'figure_path': None,
                 'cfg_type': 'InteractionSerialEvaluatorDict',
-                'n_episode': 8,
-                'stop_value': 12000
+                'stop_value': 12000,
+                'n_episode': 8
             }
         },
         'other': {
@@ -268,7 +195,7 @@ exp_config = {
             }
         },
         'on_policy': False,
-        'cuda': False,
+        'cuda': True,
         'multi_gpu': False,
         'bp_update_sync': True,
         'traj_len_inf': False,
@@ -297,7 +224,7 @@ 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/HalfCheetah-v3-SAC)
+- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/HalfCheetah-v3-SAC)
 
 ## Model Information
 <!-- Provide the basic links for the model. -->
@@ -306,14 +233,14 @@ exp_config = {
 - **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-SAC/blob/main/policy_config.py)
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-SAC/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
-- **Parameters total size:** 851.05 KB
-- **Last Update Date:** 2023-04-15
+- **Parameters total size:** 1702.11 KB
+- **Last Update Date:** 2023-09-19
 
 ## 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:** HalfCheetah-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)