Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -131.75 +/- 36.88
+      value: -185.97 +/- 99.55
       name: mean_reward
       verified: false
 ---
@@ -45,7 +45,7 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.97
+'gae_lambda': 0.96
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1694593764.90c1b31fa24d.6302.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa7e37cdeda02520838dd6ced6fa3c2bf2077155a2786b266f728c96fc80504
+size 135409

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab298b55830683910ea7159793ff98cc6026fd0aa38c731ba16dcb004275a84
+oid sha256:ce1d64d39f735d10c595eb05c7762a7f89ae779ea6bdf4d4cc02904c25e647b8
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -131.75322276691523, "std_reward": 36.876523902555654, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T08:27:20.180330"}
+{"env_id": "LunarLander-v2", "mean_reward": -185.9669304985518, "std_reward": 99.54507334838084, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T08:30:20.152417"}