Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -51.51 +/- 93.21
+      value: 132.41 +/- 47.16
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 5000000
 'learning_rate': 0.0003
 'num_envs': 1024
 'num_steps': 128

logs/events.out.tfevents.1688537584.0caa7588bd42.9320.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c81a519b02b9aca895761c12a5cc03560def1ac260d066fe6f878815b7e97ec
+size 351911

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8dcb4194d0f0fad6670694683480f7843e06d91451e12faf5785a20228da389
-size 553189
+oid sha256:2c45613936aca4d106cf2fed73d089a2426d04abfb6a43b4ce95bc552af86792
+size 553317

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -51.50794115983897, "std_reward": 93.20573428963354, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-05T04:56:43.118514"}
+{"env_id": "LunarLander-v2", "mean_reward": 132.4142827162276, "std_reward": 47.15530684566661, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-05T06:54:56.763750"}