Experiment · System One / System Two

System One

A tiny network learns a game from a slow planner, inside this tab. It plays on intuition, a cheap check catches its dangerous moves, and it asks the planner only when it is unsure.

score
0
episode
1
avg last 10
–
moves/s
–

Who decided

–

– compute units per move, now

Over the last 1,000 moves. The cost of a search depends on the state (a crowded Snake board is cheap to search), so compare with the averages only over whole games.

System One's policy

confidence threshold: below it, the planner decides

Controls

Model: untrained (random weights)

Inside System One

The live forward pass behind the current decision. Nodes light up with their real activations, and only the connections that contribute most to this decision are drawn (positive, negative). Drag to orbit. The view re-runs the forward pass for display; that work is not counted in the cost.

Training in this tab

Idle. Training takes one to two minutes on a laptop and runs in a background worker.

Share of moves per iteration

escalated by the guard agreement with planner

Mean episode score per iteration

Cost vs quality

Published results.

planner alone hybrid, no guard hybrid + guard other / baseline live game