Egocentric Keys & Transfer

Why doesn't the maze agent use a lookup table of (x, y) → action? Because it would learn nothing reusable. The agent keys its memory on what's around it, not where it is — so a lesson learned in one maze fires in another. Click a cell in Maze A to teach a situation, then see what matches in both mazes.

key the memory on
match threshold 0.70

Maze A — click a cell to teach

Maze B — never trained on

Click any open cell in Maze A.
How it works. The egocentric key for a cell is bundle( ROLE_N ⊗ filler(north) , ROLE_E ⊗ filler(east) , … ) — a hypervector summarising the kinds of things in each relative direction. Two cells with the same surroundings produce the same key no matter their coordinates or which maze they're in, so similarity transfers the lesson. The coordinate key X[x] ⊗ Y[y] is pure position: it matches the same slot in both mazes even though that slot holds a completely different situation — so the rule is misapplied, not transferred.

Tie to Neuron Lab. This is the project's cellFiller + ROLE sensing. Its route memory keys on a permutation-encoded history of these egocentric, maze-size-independent symbols, "so it transfers across mazes where a cell-indexed table can't" — the classical Q-table it once raced against was removed for exactly this reason.