Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: OpenAI/Gym/Box2d-LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 196.19 +/- 78.51
+      value: 197.47 +/- 90.44
       name: mean_reward
 ---
 
@@ -60,7 +60,23 @@ python3 -u run.py
 ```
 **run.py**
 ```python
-# [More Information Needed]
+from ding.bonus import C51Agent
+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").cfg_dict)
+# Instantiate the agent
+agent = C51Agent(
+    env_id="LunarLander-v2", exp_name="LunarLander-v2-C51", 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)
+
 ```
 </details>
 
@@ -75,7 +91,20 @@ python3 -u run.py
 ```
 **run.py**
 ```python
-# [More Information Needed]
+from ding.bonus import C51Agent
+from huggingface_ding import pull_model_from_hub
+
+# Pull model from Hugggingface hub
+policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/LunarLander-v2-C51")
+# Instantiate the agent
+agent = C51Agent(
+    env_id="LunarLander-v2", exp_name="LunarLander-v2-C51", 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)
+
 ```
 </details>
 
@@ -92,7 +121,31 @@ python3 -u train.py
 ```
 **train.py**
 ```python
-# [More Information Needed]
+from ding.bonus import C51Agent
+from huggingface_ding import push_model_to_hub
+
+# Instantiate the agent
+agent = C51Agent(env_id="LunarLander-v2", exp_name="LunarLander-v2-C51")
+# Train the agent
+return_ = agent.train(step=int(4000000), collector_env_num=8, evaluator_env_num=8, debug=False)
+# Push model to huggingface hub
+push_model_to_hub(
+    agent=agent.best,
+    env_name="OpenAI/Gym/Box2d",
+    task_name="LunarLander-v2",
+    algo_name="C51",
+    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/c51.html",
+    github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/lunarlander.html",
+    installation_guide="pip3 install DI-engine[common_env]",
+    usage_file_by_git_clone="./c51/lunarlander_c51_deploy.py",
+    usage_file_by_huggingface_ding="./c51/lunarlander_c51_download.py",
+    train_file="./c51/lunarlander_c51.py",
+    repo_id="OpenDILabCommunity/LunarLander-v2-C51",
+    create_repo=False
+)
+
 ```
 </details>
 
@@ -219,7 +272,7 @@ exp_config = {
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-C51/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
 - **Parameters total size:** 214.3 KB
-- **Last Update Date:** 2023-08-03
+- **Last Update Date:** 2023-08-07
 
 ## 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. -->