Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -172.65 +/- 92.01
+      value: -230.40 +/- 120.57
       name: mean_reward
       verified: false
 ---
@@ -44,7 +44,7 @@ model-index:
 'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.9
+'gamma': 0.5
 'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1694597841.422f4b7e0f84.10257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b730ac47bb119e42bbb829c975f1b743dd906079889b9243b1fd660b46e1c489
+size 111609

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af41d76611f3c0f9615f69eaccd54fc5e7c58f338864800bbab455f11cbddea
+oid sha256:65984944775b099898b52910e02b83d65872a552a449b08e07c3840437f71be1
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -172.64755265864335, "std_reward": 92.00983479410681, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:34:26.458092"}
+{"env_id": "LunarLander-v2", "mean_reward": -230.3989669101537, "std_reward": 120.56717029172019, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:38:22.520784"}