Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: OpenAI/Gym/Box2d-LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 246.12 +/- 10.8
+      value: 264.9 +/- 18.41
       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 = DDPGAgent(
-    env="lunarlander_continuous",
+    env_id="LunarLanderContinuous-v2",
     exp_name="LunarLander-v2-DDPG",
     cfg=cfg.exp_config,
     policy_state_dict=policy_state_dict
@@ -101,7 +101,7 @@ from huggingface_ding import pull_model_from_hub
 policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/LunarLander-v2-DDPG")
 # Instantiate the agent
 agent = DDPGAgent(
-    env="lunarlander_continuous",
+    env_id="LunarLanderContinuous-v2",
     exp_name="LunarLander-v2-DDPG",
     cfg=cfg.exp_config,
     policy_state_dict=policy_state_dict
@@ -131,7 +131,7 @@ from ding.bonus import DDPGAgent
 from huggingface_ding import push_model_to_hub
 
 # Instantiate the agent
-agent = DDPGAgent("lunarlander_continuous", exp_name="LunarLander-v2-DDPG")
+agent = DDPGAgent(env_id="LunarLanderContinuous-v2", exp_name="LunarLander-v2-DDPG")
 # Train the agent
 return_ = agent.train(step=int(4000000), collector_env_num=4, evaluator_env_num=4)
 # Push model to huggingface hub
@@ -148,7 +148,8 @@ push_model_to_hub(
     usage_file_by_git_clone="./ddpg/lunarlander_ddpg_deploy.py",
     usage_file_by_huggingface_ding="./ddpg/lunarlander_ddpg_download.py",
     train_file="./ddpg/lunarlander_ddpg.py",
-    repo_id="OpenDILabCommunity/LunarLander-v2-DDPG"
+    repo_id="OpenDILabCommunity/LunarLander-v2-DDPG",
+    create_repo=False
 )
 
 ```
@@ -172,11 +173,11 @@ exp_config = {
             'retry_waiting_time': 0.1,
             'cfg_type': 'BaseEnvManagerDict'
         },
-        'stop_value': 240,
+        'stop_value': 260,
+        'n_evaluator_episode': 8,
         'env_id': 'LunarLanderContinuous-v2',
         'collector_env_num': 8,
         'evaluator_env_num': 8,
-        'n_evaluator_episode': 8,
         'act_scale': True
     },
     'policy': {
@@ -231,9 +232,10 @@ exp_config = {
                     'render_freq': -1,
                     'mode': 'train_iter'
                 },
+                'figure_path': None,
                 'cfg_type': 'InteractionSerialEvaluatorDict',
-                'n_episode': 8,
-                'stop_value': 240
+                'stop_value': 260,
+                'n_episode': 8
             }
         },
         'other': {
@@ -281,14 +283,14 @@ exp_config = {
 - **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-DDPG/blob/main/policy_config.py)
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-DDPG/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
-- **Parameters total size:** 57.52 KB
-- **Last Update Date:** 2023-04-11
+- **Parameters total size:** 115.03 KB
+- **Last Update Date:** 2023-09-22
 
 ## 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/Box2d
 - **Task:** LunarLander-v2
 - **Gym version:** 0.25.1
-- **DI-engine version:** v0.4.6
-- **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/lunarlander.html)