Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -135.14 +/- 57.40
+      value: -135.92 +/- 143.99
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1751467604.7c6da54d0a13.27787.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f67916599dba2da759a941b3816c9849514c892047376e5e4aaa239fd99ccfd3
+size 1187890

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b6ee6d35aa725f732392261cb37b102fdbe0884c52ba4fccbfd6710bc51ec4
+oid sha256:9b5d60c2b204c19ced8eaa71795e391e7ff2736bc887adeb91682a71febf8596
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -135.13644272858255, "std_reward": 57.39682432371917, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T14:46:02.514514"}
+{"env_id": "LunarLander-v2", "mean_reward": -135.9165392596514, "std_reward": 143.99480221788966, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T14:51:52.768663"}