Dimitrius174's picture
Upload README.md with huggingface_hub
ff22813 verified
|
Raw
History Blame Contribute Delete
775 Bytes
metadata
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

Architecture

Params: 8x30 + 30 + 30x4 + 4 = 394

Usage