Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -195.87 +/- 122.73
+      value: -173.20 +/- 81.05
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 150000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
@@ -48,13 +48,14 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.02
+'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'madmage/ppo-fromscratch-LunarLander'
+'push_to_hub': True
 'batch_size': 512
 'minibatch_size': 128}
   ```

logs/events.out.tfevents.1756360245.pdemu1cml000287.353104.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63236e457dcf0e3a5891ced1f6e28ed00c38a95498b3c3c85934f436a170a5b2
+size 220957

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdafe1fc6dcefa343d60247e3f7089ced1d755548669a0c334df9e178507871f
+oid sha256:6c58c316c4b7320e639e9ba36e829027c16decfdc6b30b8e3822d37739f1407f
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -195.87367755935452, "std_reward": 122.73078787453501, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-27T20:04:56.278741"}
+{"env_id": "LunarLander-v2", "mean_reward": -173.19626616270634, "std_reward": 81.05326498056331, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-28T07:51:22.404244"}