Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -175.13 +/- 80.19
+      value: 8.81 +/- 69.55
       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.1707916300.0b5757c85070.2616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3304c1af015dcc614223477ae88797a4309bac02d192163868e12b5f5982a43d
+size 663584

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51141f29a5fd60d9f7a96a70a1e185897fcb1c4838b12131a7276001db13c08
+oid sha256:f6ca04aff66f64822aba97da008791460d2a13e5294599c0e9a57325ed9eacdb
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -175.1318036273471, "std_reward": 80.19242731994495, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-14T13:10:36.771611"}
+{"env_id": "LunarLander-v2", "mean_reward": 8.807411337415015, "std_reward": 69.54521751358743, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-14T13:27:55.446478"}