Upload README.md with huggingface_hub

README.md

@@ -9,25 +9,33 @@ tags:
 pipeline_tag: reinforcement-learning
 ---
 
-# LunarLander — 394 params, 100% landings
+# LunarLander — 394 params, 95% full landings
 
-A tiny neural network (394 parameters) that solves LunarLander-v2.
+A tiny neural network (394 parameters) solving LunarLander-v2.
 Weights: **1.5 KB**.
 
+## Performance
+
+| Metric | Value |
+|--------|-------|
+| Params | 394 |
+| Full landings (reward >= 200) | **95/100** |
+| Average reward | **258.8** |
+| Median reward | **265.8** |
+| Best reward | **310.9** |
+| Crashes (reward < 100) | 3/100 |
+| Weights size | 1.5 KB |
+
 ## Demo
 
 <video src="https://huggingface.co/Dimitrius174/lunar-lander-394-params/resolve/main/videos/lunar_lander_394_all.mp4" controls width="600"></video>
 
 ## Architecture
 
-```python
-class TinyNN(torch.nn.Module):
-    def __init__(self):
-        super().__init__()
-        self.enc = torch.nn.Linear(8, 30)
-        self.cls = torch.nn.Linear(30, 4)
-    def forward(self, x):
-        return self.cls(torch.relu(self.enc(x)))
-```
+
 
 Params: 8x30 + 30 + 30x4 + 4 = **394**
+
+## Usage
+
+