Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -159.76 +/- 111.12
+      value: -112.05 +/- 48.58
       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': 120000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1701460075.5051f8bd6bde.7580.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89dff18a656bd9be52c118a25f9ac7b244b4b55085296e5a1d882d867785c742
+size 262106

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:0cc8c34716472fbe7cea0ed180e6911af7c8ded63981cb5337d5756344853892
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -159.7640008973778, "std_reward": 111.12076488025612, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-01T19:34:51.482322"}
+{"env_id": "LunarLander-v2", "mean_reward": -112.05238654220564, "std_reward": 48.57913709192854, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-01T19:49:35.323634"}