set hyperparameters as json in model card

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -48.08 +/- 63.05
+      value: -58.74 +/- 80.66
       name: mean_reward
       verified: false
 ---
@@ -28,31 +28,5 @@ model-index:
 
   # Hyperparameters
   
-  {'seed': 0
-'torch_deterministic': True
-'cuda': True
-'track': False
-'wandb_project_name': 'cleanRL'
-'wandb_entity': None
-'capture_video': False
-'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
-'learning_rate': 0.001
-'num_envs': 8
-'num_steps': 256
-'anneal_lr': True
-'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
-'norm_adv': True
-'clip_coef': 0.2
-'clip_vloss': True
-'ent_coef': 0.01
-'vf_coef': 0.5
-'max_grad_norm': 0.5
-'target_kl': None
-'batch_size': 2048
-'minibatch_size': 512}
+  {'seed': 0, 'torch_deterministic': True, 'cuda': True, 'track': False, 'wandb_project_name': 'cleanRL', 'wandb_entity': None, 'capture_video': False, 'env_id': 'LunarLander-v2', 'total_timesteps': 100000, 'learning_rate': 0.001, 'num_envs': 8, 'num_steps': 256, 'anneal_lr': True, 'gae': True, 'gamma': 0.99, 'gae_lambda': 0.95, 'num_minibatches': 4, 'update_epochs': 4, 'norm_adv': True, 'clip_coef': 0.2, 'clip_vloss': True, 'ent_coef': 0.01, 'vf_coef': 0.5, 'max_grad_norm': 0.5, 'target_kl': None, 'batch_size': 2048, 'minibatch_size': 512}
   

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -48.07780286487041, "std_reward": 63.04813158040944, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-16T07:13:02.950893"}
+{"env_id": "LunarLander-v2", "mean_reward": -58.74375789537991, "std_reward": 80.66261767815269, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-16T07:18:40.540856"}