Upload README.md with huggingface_hub

README.md

@@ -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="PongNoFrameskip-v4", exp_name="PongNoFrameskip-v4-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/PongNoFrameskip-v4-C51")
+# Instantiate the agent
+agent = C51Agent(
+    env_id="PongNoFrameskip-v4", exp_name="PongNoFrameskip-v4-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="PongNoFrameskip-v4", exp_name="PongNoFrameskip-v4-C51")
+# Train the agent
+return_ = agent.train(step=int(20000000))
+# Push model to huggingface hub
+push_model_to_hub(
+    agent=agent.best,
+    env_name="OpenAI/Gym/Atari",
+    task_name="PongNoFrameskip-v4",
+    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/atari.html",
+    installation_guide="pip3 install DI-engine[common_env]",
+    usage_file_by_git_clone="./c51/pong_c51_deploy.py",
+    usage_file_by_huggingface_ding="./c51/pong_c51_download.py",
+    train_file="./c51/pong_c51.py",
+    repo_id="OpenDILabCommunity/PongNoFrameskip-v4-C51",
+    create_repo=False
+)
+
 ```
 </details>
 
@@ -114,7 +167,7 @@ exp_config = {
             'retry_waiting_time': 0.1,
             'cfg_type': 'BaseEnvManagerDict'
         },
-        'stop_value': 20,
+        'stop_value': 30,
         'n_evaluator_episode': 8,
         'collector_env_num': 8,
         'evaluator_env_num': 8,
@@ -166,8 +219,9 @@ exp_config = {
                     'mode': 'train_iter'
                 },
                 'figure_path': None,
+                'return_env_info': True,
                 'cfg_type': 'InteractionSerialEvaluatorDict',
-                'stop_value': 20,
+                'stop_value': 30,
                 'n_episode': 8
             }
         },
@@ -210,7 +264,7 @@ 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/anony-moose-281353441759581725/PongNoFrameskip-v4-C51?apiKey=d148cead9d59fbdabf4ef34f646a7ed95795e5bb)
+- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/PongNoFrameskip-v4-C51)
 
 ## Model Information
 <!-- Provide the basic links for the model. -->
@@ -220,7 +274,7 @@ exp_config = {
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-C51/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
 - **Parameters total size:** 55276.2 KB
-- **Last Update Date:** 2023-07-23
+- **Last Update Date:** 2023-08-09
 
 ## 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. -->