Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 219.40 +/- 130.80
+      value: 140.10 +/- 118.45
       name: mean_reward
       verified: false
 ---
@@ -28,7 +28,7 @@ model-index:
 
   # Hyperparameters
   ```python
-  {'total_timesteps': 250000
+  {'total_timesteps': 500000
 'learning_rate': 0.02
 'num_envs': 8
 'num_steps': 256

logs/events.out.tfevents.1677372933.bguisards-MBP.4016.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644133402409fbe1e25abe5a0bce59fdf2062e97a1e0d2aa95640dd70db1aa07
+size 327392

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fbb2e6aa7f0083d0d00e3b957b819ac82a06bbeb57e85dfe92c3cd5e94d8d1f
+oid sha256:be7499fc695a4acbfdbe8a850229936fec8e7f7f7481924ac85e6aae8366bd0e
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 219.40319837721307, "std_reward": 130.79869418541, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-25T19:53:39.029379"}
+{"env_id": "LunarLander-v2", "mean_reward": 140.0954640931345, "std_reward": 118.45026824377234, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-25T19:59:26.936983"}