Push agent to the Hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+---
+tags:
+- LunarLander-v2
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 22.70 +/- 91.73
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+
+  # Hyperparameters
+  ```python
+  {'repo_id': 'zhemintia/luv'
+'env_id': 'LunarLander-v2'}
+  ```
+  

logs/events.out.tfevents.1750082226.5f239a0ec163.6291.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb95c0773958adecae09683569318dc08831d0290995093a2fd45fd380fffdd0
+size 668266

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeac3ca1ece2236f59cb6838ecc30ff0126a84467bca069083a1903d6a4131f9
+size 42898

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a515e93487b018fb181e30d50c857eca3fb3c05fb58c33cab8025de9b05f08c
+size 154837

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 22.70314347654173, "std_reward": 91.72831701165269, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T14:16:35.474017"}