🎮 MPL Playground + RBD-CA Observer

Now with embedded finite observer, memory-based tracking, and intervention modes from the TRA paper!

Simulation:
Observer:
Step: 0Cells: 0

📖 Mode Guide

Off: No observer tracking

Passive: Track largest component (no memory)

+ Memory: Track with persistence bias (prefers halo overlap)

+ Guided: Memory + interventions targeting halo area

+ Random: Memory + random interventions (same budget)

🔬 Key finding: Guided and Random have the same intervention budget, but only Guided maintains identity. This proves informational coupling, not action magnitude, sustains identity!

🔥 Seed from Honestra