Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -104.13 +/- 67.22
+      value: -118.14 +/- 58.72
       name: mean_reward
       verified: false
 ---
@@ -49,7 +49,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1694552389.17a722d28ef8.9465.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f69da91ab9d358e46d6486a6e67c4b13ec8a6d9e01e1cb3aefb9c27fa8ad07
+size 135663

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebf3465c38ec32051261e720f626890cc85ca8688e353209b67003d4a9114ce
+oid sha256:5b195511dfe4ae1e219f0300d898b0358477f1495e0da367635a8edf59349810
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -104.12801344783134, "std_reward": 67.21761600900672, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:56:59.871915"}
+{"env_id": "LunarLander-v2", "mean_reward": -118.135248358771, "std_reward": 58.717373497629815, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T21:00:56.578462"}