Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 49.66 +/- 42.92
+      value: 156.65 +/- 101.52
       name: mean_reward
       verified: false
 ---
@@ -29,7 +29,7 @@ model-index:
   # Hyperparameters
   ```python
   {'exp_name': 'ppo'
-'seed': 1
+'seed': 2
 'torch_deterministic': True
 'cuda': True
 'track': False
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 8
 'num_steps': 256

logs/events.out.tfevents.1757973224.acfcdb41f287.6546.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c5577ca2f5d641d05bde307a99401d39a495bfaedb3d1ebd7089b932efd13d
+size 283113

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9bbbebce291507ee4b52086a7d81250a93abca76eb2ebf8e88ae58db47c1b6
+oid sha256:cba8f3adb0802cb8f2bb61671f64182a1b71521ffc78e11866706a5b71ad9c55
 size 43419

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:973b32f48499032d54fca8a7440644afcc64fe6347590ef5cc24284dd411a013
-size 187035
+oid sha256:cc9ee7535b67a8cb92edbe42c8c5802ca6a3f57726be4079e338bf5c730096aa
+size 93770

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 49.658121638948955, "std_reward": 42.91757720665306, "n_evaluation_episodes": 10, "eval_datetime": "2025-09-15T21:52:11.911298"}
+{"env_id": "LunarLander-v2", "mean_reward": 156.64533287533396, "std_reward": 101.5224217818913, "n_evaluation_episodes": 10, "eval_datetime": "2025-09-15T22:03:29.142117"}