Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -111.60 +/- 40.29
+      value: -102.79 +/- 49.64
       name: mean_reward
       verified: false
 ---
@@ -45,7 +45,7 @@ model-index:
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
+'num_minibatches': 8
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -56,6 +56,6 @@ model-index:
 'target_kl': None
 'repo_id': 'ahGadji/ppo-LunarLander-v2'
 'batch_size': 512
-'minibatch_size': 128}
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1716464283.98d39517c90d.21611.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09dd841d27e26aba722fa2ef2c453823ad917cebd25ca8aff141c8b4d24d6cb9
+size 108969

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51141f29a5fd60d9f7a96a70a1e185897fcb1c4838b12131a7276001db13c08
+oid sha256:89e26e3e2b35e109ddde8a86b1dcda3ce795ac587502f602cb2fbc7a9ed9e9eb
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -111.6036782949944, "std_reward": 40.29242738374692, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T11:33:11.613594"}
+{"env_id": "LunarLander-v2", "mean_reward": -102.78620665280528, "std_reward": 49.63993503762939, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T11:38:46.733238"}