Drop7 Research
← Learn

Concepts

The ideas behind every strategy in this repository, shown with animations computed by the rules engine. Read these in order and the research pages will make sense.

  1. Concept 1

    Choice, chance, and looking ahead

    Why a Drop7 strategy has to average over luck instead of hoping for it, what "depth" means, and why the strongest policy here is called fair D4.

  2. Concept 2

    Evaluating a board, and the sibling trap

    Why a model can predict how a game will go and still pick the wrong column.

  3. Concept 3

    Is more computation the answer?

    What the evidence says about deeper search, more samples, bigger models, and large training runs, including where more compute improves play and where it does not.

  4. Concept 4

    What a large-scale run would look like

    A gated proposal for search-guided self-play with every-sibling labels, including what failed locally and what must pass before any cluster run.

  5. Concept 5

    What makes a board good?

    What a Drop7 search measures when it evaluates a board, and why the current board alone is never enough.

  6. Concept 6

    Score is survival

    In this version of Drop7 almost every point comes from staying alive for one more five-move cycle, so a high score is a long game, not a spectacular chain.

  7. Concept 7

    Why one great game proves nothing

    A million-point game does not prove a million-point mean. Paired games and confidence bounds separate policy strength from luck.

  8. Concept 8

    Cheating on purpose: oracles, teachers and students

    Privileged programs measure the value of hidden knowledge and try to teach that advantage to a legal policy.

  9. Concept 9

    Four ways a program can learn Drop7

    How n-tuple networks, neural evaluators, policy-gradient learning, and Monte Carlo tree search work, with real boards and retained results.