Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: OpenAI/Gym/MuJoCo-Hopper-v3
     metrics:
     - type: mean_reward
-      value: 2698.5 +/- 901.84
+      value: 3795.27 +/- 26.06
       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="hopper", exp_name="Hopper-v3-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
+agent = PPOF(env_id="Hopper-v3", exp_name="Hopper-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/Hopper-v3-PPO")
 # Instantiate the agent
-agent = PPOF(env="hopper", exp_name="Hopper-v3-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
+agent = PPOF(env_id="Hopper-v3", exp_name="Hopper-v3-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict)
 # Continue training
 agent.train(step=5000)
 # Render the new agent performance
@@ -130,7 +131,7 @@ from ding.bonus import PPOF
 from huggingface_ding import push_model_to_hub
 
 # Instantiate the agent
-agent = PPOF(env="hopper", exp_name="Hopper-v3-PPO")
+agent = PPOF(env_id="Hopper-v3", exp_name="Hopper-v3-PPO")
 # Train the agent
 return_ = agent.train(step=int(10000000), collector_env_num=4, evaluator_env_num=4, debug=False)
 # 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 DI-engine[common_env]
+pip3 install "cython<3"
+pip3 install DI-engine[common_env,video]
 ''',
     usage_file_by_git_clone="./ppo/hopper_ppo_deploy.py",
     usage_file_by_huggingface_ding="./ppo/hopper_ppo_download.py",
     train_file="./ppo/hopper_ppo.py",
-    repo_id="OpenDILabCommunity/Hopper-v3-PPO"
+    repo_id="OpenDILabCommunity/Hopper-v3-PPO",
+    create_repo=False
 )
 
 ```
@@ -191,19 +194,22 @@ exp_config = {
     'epoch_per_collect': 10,
     'batch_size': 320,
     'learning_rate': 0.0003,
+    'lr_scheduler': None,
     'weight_decay': 0,
     'value_weight': 0.5,
     'entropy_weight': 0.01,
     'clip_ratio': 0.2,
     'adv_norm': True,
-    'value_norm': 'symlog',
+    'value_norm': 'baseline',
     'ppo_param_init': True,
     'grad_norm': 0.5,
     'n_sample': 3200,
     'unroll_len': 1,
     'deterministic_eval': True,
     'model': {},
-    'cfg_type': 'PPOFPolicyDict'
+    'cfg_type': 'PPOFPolicyDict',
+    'env_id': 'Hopper-v3',
+    'exp_name': 'Hopper-v3-PPO'
 }
 
 ```
@@ -221,13 +227,13 @@ exp_config = {
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/Hopper-v3-PPO/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
 - **Parameters total size:** 375.3 KB
-- **Last Update Date:** 2023-04-13
+- **Last Update Date:** 2023-09-24
 
 ## 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:** Hopper-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)