Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -88.30 +/- 87.78
+      value: -121.56 +/- 14.74
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1703596394.cybertron.1616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39795ebf1b2b825dcc12d609e99b59f7c6973894f38a14ddaedd01faab34fb7
+size 133444

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4a03fa728a33b1506a43ac3083bbddd5cb59ee0f8d480281fbb3d8c2db6cc20
+oid sha256:1bb1c8ae9e363c8b45a0ea950d0c91e82cefbb0fe3d5d36668e8902fed87eea5
 size 672534

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -88.30457757926787, "std_reward": 87.78342986788695, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T21:12:39.297008"}
+{"env_id": "LunarLander-v2", "mean_reward": -121.55896973720397, "std_reward": 14.741084119426633, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T21:15:37.396587"}