Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -5.81 +/- 55.17
+      value: -33.21 +/- 68.26
       name: mean_reward
       verified: false
 ---
@@ -25,37 +25,6 @@ model-index:
   # PPO Agent Playing LunarLander-v2
 
   This is a trained model of a PPO agent playing LunarLander-v2.
-    
+
   # 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': 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': 'HadrienCr/LunarLander'
-'batch_size': 512
-'minibatch_size': 128}
-  ```
   

logs/events.out.tfevents.1719242562.65dd396b321c.5834.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a72c9d5478ddfa24634e0edc25e8ab4fd288b1f88176276ad919a740dd77e58
+size 169267

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ca04aff66f64822aba97da008791460d2a13e5294599c0e9a57325ed9eacdb
-size 42898
+oid sha256:54596bb2d29523fc766c387764f4977ecb94541ba00c8d2d35fc4867f45dee5a
+size 23144

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -5.811936512939699, "std_reward": 55.16955533862541, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-23T16:20:18.427115"}
+{"env_id": "LunarLander-v2", "mean_reward": -33.213919655010784, "std_reward": 68.25760470673174, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-24T15:24:47.677681"}