spec_version: 1
name: orthorl
type: space
runtime: fastapi
app: server.app:app
port: 7860
version: '2.0.0'
description: >
  OrthoRL: RL environment for orthodontic treatment planning. 24-step
  sequential aligner staging in SE(3) space with diagnostic tools,
  pharmacokinetic force decay, strategy-dependent rewards, and adaptive
  difficulty. Trained on 1,063 real patient profiles from Tsinghua dataset.
tags:
  - openenv
  - dental
  - orthodontics
  - se3
  - medical-ai
  - reinforcement-learning
  - treatment-planning