Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -150.59 +/- 97.76
+      value: -2.20 +/- 71.54
       name: mean_reward
       verified: false
 ---
@@ -28,6 +28,6 @@ model-index:
 
   # Hyperparameters
   ```python
-  {'exp_name': 'ppo''seed': 1'torch_deterministic': True'cuda': True'track': False'wandb_project_name': 'cleanRL''wandb_entity': None'capture_video': False'env_id': 'LunarLander-v2''total_timesteps': 50000'learning_rate': 0.00025'num_envs': 4'num_steps': 128'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'repo_id': 'wooii/ppo-LunarLander-v2-2''batch_size': 512'minibatch_size': 128}
+  {'exp_name': 'ppo''seed': 1'torch_deterministic': True'cuda': True'track': False'wandb_project_name': 'cleanRL''wandb_entity': None'capture_video': False'env_id': 'LunarLander-v2''total_timesteps': 500000'learning_rate': 0.00025'num_envs': 4'num_steps': 128'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'repo_id': 'wooii/ppo-LunarLander-v2-2''batch_size': 512'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1696466755.6eaa3ccf779c.4023.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e20abeb204fb08f12dbe4451a355162466ec4b3bd1ee85489e389258ca6c4cc
+size 664042

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a6748cee3444894102db06ecc10eb21168fdd67939c4d5bf3a05379f763ac8
+oid sha256:20db8ae322208fb28b7b4f1624fc7be0a5e8f7f56a3fa8fd2c2f292718a3769e
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -150.5917066883356, "std_reward": 97.76216456777576, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-05T00:45:10.450614"}
+{"env_id": "LunarLander-v2", "mean_reward": -2.1984204207338665, "std_reward": 71.5408860252107, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-05T01:02:19.760179"}