Push PPO LunarLander-v2 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

@@ -1,10 +1,11 @@
 ---
-library_name: stable-baselines3
 tags:
 - LunarLander-v2
+- ppo
 - deep-reinforcement-learning
 - reinforcement-learning
-- stable-baselines3
+- custom-implementation
+- deep-rl-course
 model-index:
 - name: PPO
   results:
@@ -16,22 +17,24 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 264.12 +/- 15.25
+      value: 35.32 +/- 57.58
       name: mean_reward
       verified: false
 ---
 
-# **PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO** agent playing **LunarLander-v2**
-using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+# PPO Agent Playing LunarLander-v2
 
-## Usage (with Stable-baselines3)
-TODO: Add your code
+This is a PPO agent trained from scratch using PyTorch.
 
+## Evaluation
 
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+Mean reward: 35.32 +/- 57.58
 
-...
-```
+Evaluation episodes: 10
+
+## Files
+
+- `model.pt` — trained PPO model weights
+- `replay.mp4` — replay video
+- `results.json` — evaluation results
+- `hyperparameters.json` — training configuration

hyperparameters.json

@@ -0,0 +1,4 @@
+{
+  "batch_size": 512,
+  "minibatch_size": 128
+}

logs/events.out.tfevents.1789204122.cfd3f46d3e47.803.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8667f63367c8a2404c82ab10205e829e5be019e845fec2ad1a3d077ae4731fd0
+size 669151

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84b61b090ff17e6fb838e8b70c3ddd2e873d9b102c5f1712a5ca1e1b69a2938
+size 43419

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf1311c3e08ba64f67f520765e9a8e715c6422b6ec9ccf85cec2f2d1a5729af
+size 185877

results.json

@@ -1 +1,7 @@
-{"mean_reward": 264.11657990000003, "std_reward": 15.246895270158488, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-09-11T06:20:13.536000"}
+{
+  "env_id": "LunarLander-v2",
+  "mean_reward": 35.31697097242282,
+  "std_reward": 57.58304267882205,
+  "n_evaluation_episodes": 10,
+  "eval_datetime": "2026-09-12T09:17:46.857908"
+}