Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: -212.65 +/- 72.55
+      value: -160.37 +/- 54.94
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ wandb_project_name: cleanRL
 wandb_entity: None
 capture_video: False
 env_id: LunarLander-v3
-total_timesteps: 5000
+total_timesteps: 50000
 learning_rate: 0.00025
 num_envs: 4
 num_steps: 128

logs/events.out.tfevents.1755442506.DESKTOP-92SAKPB.185095.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:621700cfd24cf0c69564d4c7099abcb57e183cd39998e85b63555ff41667ac98
+size 50413

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2afe2ef2ab266f778ac78e7757cf603b67b6b37238227b185c3cc82738fa84
+oid sha256:56b1dd36a1e2fb61af3b3c245aaf746137882c68175ee02a7eb88fa7888045a0
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v3", "mean_reward": -212.6519075971577, "std_reward": 72.54742792484979, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-17T17:52:24.873122"}
+{"env_id": "LunarLander-v3", "mean_reward": -160.36789987204025, "std_reward": 54.93750345011522, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-17T17:56:12.399073"}