Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 12.28 +/- 58.85
+      value: 104.83 +/- 18.01
       name: mean_reward
       verified: false
 ---
@@ -27,6 +27,4 @@ model-index:
   This is a trained model of a PPO agent playing LunarLander-v2.
 
   # Hyperparameters
-  See the GitHub for full info and the journey on creating this on the surface not particularly exciting model: https://github.com/MattStammers/PPO_Lander_Implementation 
-
-  It took me 8 attempts to get the score to nearly reach 0 using a cleanRL implementation and WandB metric tracking.
+  

logs/events.out.tfevents.1695069059.rhmmedcatt-ProLiant-ML350-Gen10.23223.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6534fa50be0408aa0878e5d8bb264ea7a140e986a43eac761528e7b199967c45
+size 2448271

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6580e6d7fc80fe15b0474e054c9b8bc90755c669b325bd6fad8e401e0dca3037
+oid sha256:fa3561982d92893028d31ca5cfc8a13c9593138e5475bee965053e2e44f111d1
 size 147301

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 12.277358919852976, "std_reward": 58.846356396395514, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-18T19:16:52.733136"}
+{"env_id": "LunarLander-v2", "mean_reward": 104.82761980859839, "std_reward": 18.014334589706, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-19T00:59:32.656971"}