README.md

metadata

title: Minimal Self Awareness
emoji: 👁
colorFrom: red
colorTo: blue
sdk: gradio
sdk_version: 6.0.1
app_file: app.py
pinned: false
license: other
short_description: 'this space  documents the 3 minimum requirements 4awareness '
thumbnail: >-
  https://cdn-uploads.huggingface.co/production/uploads/685edcb04796127b024b4805/WD3U3Qw3UGb5KmytR3yS5.png

Minimal Self in a 3×3 World — RFT Cognitive Core

This Space runs the full implementation of the Rendered Frame Theory (RFT) Minimal Self: a 3×3 embodied agent that learns to predict, explore, and socially mimic using transparent Q-learning and observer-anchored simulation.

Features

• Agent state: [x, y, body_bit] with optional obstacle and social entity
• Counterfactual prediction loop: “If I do this, where will I be?”
• Q-learning with ε-greedy exploration and reward shaping
• Metrics: predictive rate, coherence (C_min), body bit strength, and toy integrated information (Φ_min)
• Optional moving obstacle and social mimicry
• Live plots and downloadable results.csv

How to Use

1. Choose number of steps, learning rate, and reward type.
2. Toggle obstacle or social entity.
3. Click Run simulation to generate metrics and path plots.
4. Download results as CSV for further analysis.

Experiments

This agent supports 7 experimental modes:

• Passive centering
• Obstacle avoidance
• Explore & Grow
• Social mimicry
• Full social cognition

Citation

Grinstead, L. (2025). Minimal Self in a 3×3 World: RFT Cognitive Core.
Independent Researcher, Infinite Codex Project.

License

This Space is governed by a custom Codex license. All reuse requires explicit permission and citation.
See LICENSE file for details.

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference