Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -149.15 +/- 80.05
+      value: -19.89 +/- 54.51
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1697379101.3eb9289d18f7.12371.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960cffd3d95ffe470496d673cfe486ba24282f35633e011cac40920532cb7ed5
+size 675237

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
+oid sha256:95d2db815a33646e84e478628a4da4f156c95480a7b55276eebdc219ec4fcd18
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -149.14553802743006, "std_reward": 80.05316891648808, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-15T14:04:21.452201"}
+{"env_id": "LunarLander-v2", "mean_reward": -19.886964074058827, "std_reward": 54.51478798679074, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-15T14:26:02.426613"}