| license: mit | |
| language: en | |
| tags: | |
| - reinforcement-learning | |
| - lunar-lander | |
| - tiny-model | |
| - 394-params | |
| pipeline_tag: reinforcement-learning | |
| # LunarLander — 394 params, 95% full landings | |
| 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 | |
| Params: 8x30 + 30 + 30x4 + 4 = **394** | |
| ## Usage | |