Approaches

Every strategy family and approach directory in the repository, with notes on how each strategy works and what its evidence showed.

Afterstate learning

1 approaches

Judge the position a move leaves behind rather than the move itself, and build training data in which every column the player could have chosen has been measured, not guessed.

1 written · 0 draft · 1 total · family guide

Baselines and diagnostics

7 approaches

Simple reference players, engine cross-checks, and per-move counters provide the measuring instruments for policy research.

7 written · 0 draft · 7 total · family guide

Constructive and reservoir policies

7 approaches

Build structures that pay off later and survive repeated row rises instead of taking only immediate points.

7 written · 0 draft · 7 total · family guide

Depth-4 search and long outcomes

4 approaches

Judges moves over 25-step continuations, then tries to retain only choices that survive the longer view.

4 written · 0 draft · 4 total · family guide

Fair expectimax

12 approaches

Look a few moves ahead, take the best column on your own turns, and average over every sampled disc the game might deal.

12 written · 0 draft · 12 total · family guide

Hand-built heuristics and shallow search

15 approaches

Scores visible board traits, adds them together, and plays the highest-valued column.

15 written · 0 draft · 15 total · family guide

Lifetime objective

24 approaches

Judge a move by how much longer the game will still last, rather than by how many points it scores right now.

23 written · 0 draft · 24 total · family guide

N-tuple networks and learning from play

12 approaches

Learn what makes a Drop7 board good from small cell patterns and millions of self-play games.

12 written · 0 draft · 12 total · family guide

Oracle and curriculum research

8 approaches

Let a planner cheat (show it the hidden numbers and the discs still to come) then try to teach a player who cannot cheat.

8 written · 0 draft · 8 total · family guide

Terminal policy iteration

6 approaches

Play every move forward many times, then override the reference only when one move produces clearly longer, higher-scoring games.

6 written · 0 draft · 6 total · family guide

Tree search

4 approaches

Instead of examining every column to a fixed depth, grow the look-ahead only where it looks promising, guided by quick simulated playouts.

4 written · 0 draft · 4 total · family guide

Value and policy learning

12 approaches

Instead of searching ahead, train a model on past games to judge a board or pick a column, and learn why that kept failing.

12 written · 0 draft · 12 total · family guide