Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -125.67 +/- 66.63
+      value: -144.04 +/- 92.67
       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': 5
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1718028097.887b5cfc0142.23982.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68441856c1b0f361d56349b21212e539980f0f3246cc999c76d45d535cf9b54
+size 113055

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:f8f0be46682e01a03544f9fce03f5e59e41d26bcc9733d106a50cccba6f4e836
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -125.67078278392061, "std_reward": 66.62954785199712, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T14:00:57.530843"}
+{"env_id": "LunarLander-v2", "mean_reward": -144.04116374766815, "std_reward": 92.6671262820496, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T14:02:23.658153"}