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: 2531.25 +/- 3547.33
+      value: 8300.0 +/- 0.0
       name: mean_reward
 ---
 
@@ -60,23 +60,7 @@ python3 -u run.py
 ```
 **run.py**
 ```python
-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"))
-# Instantiate the agent
-agent = C51Agent(
-    env="QbertNoFrameskip", exp_name="QbertNoFrameskip-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)
-
+# [More Information Needed]
 ```
 </details>
 
@@ -91,20 +75,7 @@ python3 -u run.py
 ```
 **run.py**
 ```python
-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/QbertNoFrameskip-v4-C51")
-# Instantiate the agent
-agent = C51Agent(
-    env="QbertNoFrameskip", exp_name="QbertNoFrameskip-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)
-
+# [More Information Needed]
 ```
 </details>
 
@@ -121,30 +92,7 @@ python3 -u train.py
 ```
 **train.py**
 ```python
-from ding.bonus import C51Agent
-from huggingface_ding import push_model_to_hub
-
-# Instantiate the agent
-agent = C51Agent(env="QbertNoFrameskip", exp_name="QbertNoFrameskip-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="QbertNoFrameskip-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/qbert_c51_deploy.py",
-    usage_file_by_huggingface_ding="./c51/qbert_c51_download.py",
-    train_file="./c51/qbert_c51.py",
-    repo_id="OpenDILabCommunity/QbertNoFrameskip-v4-C51"
-)
-
+# [More Information Needed]
 ```
 </details>
 
@@ -171,7 +119,8 @@ exp_config = {
         'collector_env_num': 8,
         'evaluator_env_num': 8,
         'env_id': 'QbertNoFrameskip-v4',
-        'frame_stack': 4
+        'frame_stack': 4,
+        'env_wrapper': 'atari_default'
     },
     'policy': {
         'model': {
@@ -216,6 +165,7 @@ exp_config = {
                     'render_freq': -1,
                     'mode': 'train_iter'
                 },
+                'figure_path': None,
                 'cfg_type': 'InteractionSerialEvaluatorDict',
                 'stop_value': 30000,
                 'n_episode': 8
@@ -260,7 +210,7 @@ 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/zjowowen/QbertNoFrameskip-v4-C51)
+- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/anony-moose-281353441759581725/QbertNoFrameskip-v4-C51?apiKey=d148cead9d59fbdabf4ef34f646a7ed95795e5bb)
 
 ## Model Information
 <!-- Provide the basic links for the model. -->
@@ -270,13 +220,13 @@ exp_config = {
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-C51/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
 - **Parameters total size:** 55276.2 KB
-- **Last Update Date:** 2023-05-18
+- **Last Update Date:** 2023-07-24
 
 ## 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/Atari
 - **Task:** QbertNoFrameskip-v4
 - **Gym version:** 0.25.1
-- **DI-engine version:** v0.4.7
-- **PyTorch version:** 1.7.1
+- **DI-engine version:** v0.4.8
+- **PyTorch version:** 2.0.1+cu117
 - **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html)