Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: OpenAI/Gym/ClassicControl-Pendulum-v1
     metrics:
     - type: mean_reward
-      value: -243.93 +/- 144.62
+      value: -231.49 +/- 235.68
       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 = SACAgent(
-    env="pendulum", exp_name="Pendulum-v1-SAC", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
+    env_id="Pendulum-v1", exp_name="Pendulum-v1-SAC", 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/Pendulum-v1-SAC")
 # Instantiate the agent
 agent = SACAgent(
-    env="pendulum",
+    env_id="Pendulum-v1",
     exp_name="Pendulum-v1-SAC",
     cfg=cfg.exp_config,
     policy_state_dict=policy_state_dict
@@ -128,7 +128,7 @@ from ding.bonus import SACAgent
 from huggingface_ding import push_model_to_hub
 
 # Instantiate the agent
-agent = SACAgent("pendulum", exp_name="Pendulum-v1-SAC")
+agent = SACAgent(env_id="Pendulum-v1", exp_name="Pendulum-v1-SAC")
 # Train the agent
 return_ = agent.train(step=int(4000000), collector_env_num=8, evaluator_env_num=8)
 # Push model to huggingface hub
@@ -145,7 +145,8 @@ push_model_to_hub(
     usage_file_by_git_clone="./sac/pendulum_sac_deploy.py",
     usage_file_by_huggingface_ding="./sac/pendulum_sac_download.py",
     train_file="./sac/pendulum_sac.py",
-    repo_id="OpenDILabCommunity/Pendulum-v1-SAC"
+    repo_id="OpenDILabCommunity/Pendulum-v1-SAC",
+    create_repo=False
 )
 
 ```
@@ -170,10 +171,11 @@ exp_config = {
             'cfg_type': 'BaseEnvManagerDict'
         },
         'stop_value': -250,
+        'n_evaluator_episode': 8,
+        'env_id': 'Pendulum-v1',
         'collector_env_num': 10,
         'evaluator_env_num': 8,
-        'act_scale': True,
-        'n_evaluator_episode': 8
+        'act_scale': True
     },
     'policy': {
         'model': {
@@ -226,9 +228,10 @@ exp_config = {
                     'render_freq': -1,
                     'mode': 'train_iter'
                 },
+                'figure_path': None,
                 'cfg_type': 'InteractionSerialEvaluatorDict',
-                'n_episode': 8,
-                'stop_value': -250
+                'stop_value': -250,
+                'n_episode': 8
             }
         },
         'other': {
@@ -237,7 +240,7 @@ exp_config = {
             }
         },
         'on_policy': False,
-        'cuda': False,
+        'cuda': True,
         'multi_gpu': False,
         'bp_update_sync': True,
         'traj_len_inf': False,
@@ -274,14 +277,14 @@ exp_config = {
 - **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-SAC/blob/main/policy_config.py)
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-SAC/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
-- **Parameters total size:** 202.52 KB
-- **Last Update Date:** 2023-04-30
+- **Parameters total size:** 405.03 KB
+- **Last Update Date:** 2023-09-23
 
 ## 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/ClassicControl
 - **Task:** Pendulum-v1
 - **Gym version:** 0.25.1
-- **DI-engine version:** v0.4.7
-- **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/pendulum.html)