Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 1.78 +/- 62.26
+      value: -16.76 +/- 73.50
       name: mean_reward
       verified: false
 ---
@@ -25,7 +25,7 @@ model-index:
   # PPO Agent Playing LunarLander-v2
 
   This is a trained model of a PPO agent playing LunarLander-v2.
-
+    
   # Hyperparameters
   ```python
   {'exp_name': 'ppo'
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 800000
+'total_timesteps': 1000000
 'learning_rate': 5e-05
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1714999499.29e4c9a197b0.6577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b3e09b500dc9eeedec11545cfd6ba26e6f0ffae694710fff794019f8b918e23
+size 1443001

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2f3e185724e0a971bcf8f1155b7348090f2021d11696227e79ca16df233ce3c
+oid sha256:f50913507097a26583a4c9a1820970125e7d8a8626aabc2cfa00d9c871087c1d
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 1.7838630532821327, "std_reward": 62.25949755636738, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-06T00:55:00.024315"}
+{"env_id": "LunarLander-v2", "mean_reward": -16.75519860903405, "std_reward": 73.49554118778019, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-06T13:07:34.396939"}