Spaces:
Sleeping
Download README.md from 1akshith/interior-env: direct link, hf CLI and curl.
- Browser
- Download file 2.67 kB
-
https://huggingface.co/spaces/1akshith/interior-env/resolve/main/README.md
- Command line
-
hf download hf://spaces/1akshith/interior-env/README.md
-
curl -L -o README.md https://huggingface.co/spaces/1akshith/interior-env/resolve/main/README.md
title: Spatial Interior Engine
emoji: ๐๏ธ
colorFrom: blue
colorTo: purple
sdk: docker
app_port: 7860
tags:
- openenv
pinned: false
license: mit
Spatial Interior Sandbox (OpenEnv Submission)
A highly advanced 2D Spatial Engine combining "Furniture Tetris" with architectural logic constraints and "A* Pathfinding" for Human Flow validation.
๐ Real-World Utility (Domain)
This environment accurately evaluates an AI agent's ability to manipulate physical objects in a 2D coordinate space while preserving accessibility pathways and honoring rigorous interior design constraints. Floor planning, constraint-based packing, and layout flow optimization are genuine robotics and architectural planning problems, moving far past toy games into real-world spatial physics evaluation.
๐ Observation Space
The observation space provides a completely typed dictionary of the entire room state:
room_size: Tuple(width, height)defining the physical 2D grid.door_position: Fixed entry point coordinate.windows: List of(x, y)coordinates acting as structural constraints.unplaced_items: Inventory of remaining{id, width, height, rules}items.placed_items: Dictionary mapping item IDs toPlacedFurniture(x, y, rotation).feedback_logs: Real-time compiler feedback indicating violations per step.
๐ฎ Action Space
Agents submit typed JSON payloads to execute positional maneuvers.
{
"action_type": "place_item", // Or 'remove_item' / 'no_op'
"item": "sofa",
"x": 4,
"y": 5,
"rotation": 90
}
๐ Reward Design & Difficulty
- Varying Dense Progress Signals: The environment returns a partial reward (+0.5 to +1.0) for every successful, non-overlapping placement that instantly resolves pending architectural rules. Backtracking drops the reward by -0.1, and collisions hit -1.0.
- 1.0 Perfect Completion Score: Total episode
scorescales to1.0if the room layout is cleanly solved in minimal steps, degrading slowly for wasted actions (efficiency scaling). - Difficulty Grading: We scale complexity via
easy(8 items),medium(10 items), andhard(15 items) tasks, measuring true spatial capability rather than pure luck. (Random placing fails at 0%).
๐ ๏ธ Setup & Inference Evaluator
Fully supported inference.py script provided in the repository root for automated valuation.
- Install SDK Tools: run
uv lock&&pip install openenv-core - Execute Agent Benchmark:
$env:HF_TOKEN="your_hf_token"
python inference.py --task hard
- Execute Interactive Dashboard UI:
python -m uvicorn server.app:app --port 7860