Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -225.06 +/- 161.42
+      value: -202.88 +/- 118.29
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 10000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1759864565.Anatolijs-MacBook-Pro.local.2931.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6645306cc457889bf587ecefab350f98a696741279c36c8602263e181b2b75e2
+size 22346366

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ffa14119954e21f80bdaf90b3c0a13db930a9e1a96fdccac2bb4c7a87b06767
+oid sha256:2a12e536f7b8c8dd76391e078d8f9f7435dd78f3ed6495635b18e230e2635cd0
 size 43291

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -225.06479516637427, "std_reward": 161.41914250454255, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-07T21:32:56.792510"}
+{"env_id": "LunarLander-v2", "mean_reward": -202.88296026336852, "std_reward": 118.28648469003252, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-08T00:53:22.800084"}