Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.09 +/- 73.73
+      value: -39.79 +/- 53.83
       name: mean_reward
       verified: false
 ---
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 16
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1677956809.bcf0fbd46106.10347.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ec5153059b300ae0843e8719323cb1fb584174d1ac71fef9d981de8cafa277
+size 198007

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be524e25501066b5b4dede8fae9a72f5c135a546364269c983124322fb0e8a81
+oid sha256:f3c38d0db4a3f6e241118f7f95b991e20603291b0c20430ba482040d5d190b1a
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -140.09413747824232, "std_reward": 73.72768512266258, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T19:05:35.472570"}
+{"env_id": "LunarLander-v2", "mean_reward": -39.789778345175165, "std_reward": 53.832931037699765, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T19:18:47.651387"}