Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: OpenAI/Gym/Atari-QbertNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 16375.0 +/- 0.0
+      value: 17175.0 +/- 0.0
       name: mean_reward
 ---
 
@@ -45,7 +45,7 @@ This is a simple **DQN** implementation to OpenAI/Gym/Atari **QbertNoFrameskip-v
 git clone https://github.com/opendilab/huggingface_ding.git
 pip3 install -e ./huggingface_ding/
 # install environment dependencies if needed
-pip3 install DI-engine[common_env]
+pip3 install DI-engine[common_env,video]
 ```
 </details>
 
@@ -60,7 +60,23 @@ python3 -u run.py
 ```
 **run.py**
 ```python
-# [More Information Needed]
+from ding.bonus import DQNAgent
+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 = DQNAgent(
+    env_id="QbertNoFrameskip-v4", exp_name="QbertNoFrameskip-v4-DQN", 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 DQNAgent
+from huggingface_ding import pull_model_from_hub
+
+# Pull model from Hugggingface hub
+policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/QbertNoFrameskip-v4-DQN")
+# Instantiate the agent
+agent = DQNAgent(
+    env_id="QbertNoFrameskip-v4", exp_name="QbertNoFrameskip-v4-DQN", 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 +121,32 @@ python3 -u train.py
 ```
 **train.py**
 ```python
-# [More Information Needed]
+from ding.bonus import DQNAgent
+from huggingface_ding import push_model_to_hub
+
+# Instantiate the agent
+agent = DQNAgent(env_id="QbertNoFrameskip-v4", exp_name="QbertNoFrameskip-v4-DQN")
+# Train the agent
+return_ = agent.train(step=int(20000000), collector_env_num=8, evaluator_env_num=8, debug=False)
+print("-----wandb url is----:", return_.wandb_url)
+# Push model to huggingface hub
+push_model_to_hub(
+    agent=agent.best,
+    env_name="OpenAI/Gym/Atari",
+    task_name="QbertNoFrameskip-v4",
+    algo_name="DQN",
+    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/dqn.html",
+    github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html",
+    installation_guide="pip3 install DI-engine[common_env,video]",
+    usage_file_by_git_clone="./dqn/qbert_dqn_deploy.py",
+    usage_file_by_huggingface_ding="./dqn/qbert_dqn_download.py",
+    train_file="./dqn/qbert_dqn.py",
+    repo_id="OpenDILabCommunity/QbertNoFrameskip-v4-DQN",
+    create_repo=False
+)
+
 ```
 </details>
 
@@ -217,13 +271,13 @@ exp_config = {
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-DQN/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
 - **Parameters total size:** 55703.03 KB
-- **Last Update Date:** 2023-07-23
+- **Last Update Date:** 2023-10-08
 
 ## 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/Atari
 - **Task:** QbertNoFrameskip-v4
 - **Gym version:** 0.25.1
-- **DI-engine version:** v0.4.8
+- **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/atari.html)