Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: OpenAI/Gym/Atari-SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 685.0 +/- 0.0
+      value: 700.0 +/- 0.0
       name: mean_reward
 ---
 
@@ -67,10 +67,10 @@ 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="SpaceInvadersNoFrameskip", exp_name="SpaceInvadersNoFrameskip-v4-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
+    env_id="SpaceInvadersNoFrameskip-v4", exp_name="SpaceInvadersNoFrameskip-v4-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
 )
 # Continue training
 agent.train(step=5000)
@@ -98,7 +98,7 @@ from huggingface_ding import pull_model_from_hub
 policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/SpaceInvadersNoFrameskip-v4-PPO")
 # Instantiate the agent
 agent = PPOF(
-    env="SpaceInvadersNoFrameskip", exp_name="SpaceInvadersNoFrameskip-v4-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
+    env_id="SpaceInvadersNoFrameskip-v4", exp_name="SpaceInvadersNoFrameskip-v4-PPO", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
 )
 # Continue training
 agent.train(step=5000)
@@ -125,7 +125,7 @@ from ding.bonus import PPOF
 from huggingface_ding import push_model_to_hub
 
 # Instantiate the agent
-agent = PPOF(env="SpaceInvadersNoFrameskip", exp_name="SpaceInvadersNoFrameskip-v4-PPO")
+agent = PPOF(env_id="SpaceInvadersNoFrameskip-v4", exp_name="SpaceInvadersNoFrameskip-v4-PPO")
 # Train the agent
 return_ = agent.train(step=int(10000000))
 # Push model to huggingface hub
@@ -142,7 +142,8 @@ push_model_to_hub(
     usage_file_by_git_clone="./ppo/spaceinvaders_ppo_deploy.py",
     usage_file_by_huggingface_ding="./ppo/spaceinvaders_ppo_download.py",
     train_file="./ppo/spaceinvaders_ppo.py",
-    repo_id="OpenDILabCommunity/SpaceInvadersNoFrameskip-v4-PPO"
+    repo_id="OpenDILabCommunity/SpaceInvadersNoFrameskip-v4-PPO",
+    create_repo=False
 )
 
 ```
@@ -181,7 +182,9 @@ exp_config = {
         'actor_head_hidden_size': 128,
         'critic_head_hidden_size': 128
     },
-    'cfg_type': 'PPOFPolicyDict'
+    'cfg_type': 'PPOFPolicyDict',
+    'env_id': 'SpaceInvadersNoFrameskip-v4',
+    'exp_name': 'SpaceInvadersNoFrameskip-v4-PPO'
 }
 
 ```
@@ -199,13 +202,13 @@ exp_config = {
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/SpaceInvadersNoFrameskip-v4-PPO/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
 - **Parameters total size:** 11501.55 KB
-- **Last Update Date:** 2023-06-16
+- **Last Update Date:** 2023-09-21
 
 ## 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:** SpaceInvadersNoFrameskip-v4
 - **Gym version:** 0.25.1
-- **DI-engine version:** v0.4.8
-- **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/atari.html)