Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 65.18 +/- 35.18
+      value: -26.89 +/- 16.88
       name: mean_reward
       verified: false
 ---
@@ -44,7 +44,7 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.98
-'gae_lambda': 0.9
+'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 5
 'norm_adv': True

logs/events.out.tfevents.1701203818.e705ad2e6486.29367.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d44cfc14a6593b161662103ef9dcb386077764b9582ce615c9f93c992f32dd
+size 118391

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d233696b66e59ceff73369a454af19082ec83746054be05354a2a4cd45eb2ba
+oid sha256:270787e1cf5cc745903265ccea35c4ee67565d2a545c05b7a821a3c7ff38e7ef
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 65.18006046677014, "std_reward": 35.17955382712036, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:35:36.537981"}
+{"env_id": "LunarLander-v2", "mean_reward": -26.889279898953795, "std_reward": 16.880666246087554, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:40:32.452016"}