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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.