Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -179.26 +/- 103.99
+      value: -222.96 +/- 120.51
       name: mean_reward
       verified: false
 ---
@@ -44,7 +44,7 @@ model-index:
 'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.2
+'gamma': 0.1
 'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1694598949.422f4b7e0f84.14786.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0f06d5921fbc4a0a406fb503227a9d6401498fb24f96e192cfcd66d27fae1c
+size 103799

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a5357d3b22c7be0f5f7fef2d7e85f5fa1d5fd7f79a5045c27e776d780cb6b79
+oid sha256:7880036abd2942bd09593a88fadef93d1a3f8aa72ca53912e82f04d067b2afe7
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -179.25846645191797, "std_reward": 103.9928330954927, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:49:41.588060"}
+{"env_id": "LunarLander-v2", "mean_reward": -222.95883281534617, "std_reward": 120.50891227216498, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:56:53.943301"}