Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -136.50 +/- 103.16
+      value: 183.35 +/- 68.76
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1727311261.Spyros.359860.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7b203ed9134fc7ba8a5c42333d092760aeae77eef7e2dbc4843fd81bde4fae
+size 1368864

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773f52359f8b8a12d51d39e534f9900ffd15228a79b664996a63689bef8111dd
+oid sha256:fdd360bc4217adb9a1f607610b8740465e87f1cb7a7e15a4b4d2885ecd6c97bd
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -136.49679556971566, "std_reward": 103.16154241079843, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-26T03:40:38.092202"}
+{"env_id": "LunarLander-v2", "mean_reward": 183.3512511608174, "std_reward": 68.75995047164085, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-26T04:48:51.783583"}