Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -198.89 +/- 69.88
+      value: -5.81 +/- 55.17
       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.1719158691.64ec8e61c2a3.22062.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91aa91efd321b595fcde4f9bf2f9786697b517054631553c2b2743a6ed86937
+size 663571

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": -198.88842446313498, "std_reward": 69.8792853810673, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-23T15:13:27.130939"}
+{"env_id": "LunarLander-v2", "mean_reward": -5.811936512939699, "std_reward": 55.16955533862541, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-23T16:20:18.427115"}