General value model

One TypeScript trainer with a switch on the front: point it at a hand-written heuristic, at a privileged planner that knows the future, at a self-improving fitted target, or at a contrastive comparison of columns, and it fits a board or policy model from that source.

The label above is about the training side. One of the four selectable teachers is the perfect-information oracle, which reads the future disc and reveal streams and is therefore never a legal player. What comes out of the trainer is a model over the public board, the visible next disc and the rise clock, and it is only that frozen student — not its teacher — that any strength claim could ever be about.

The intuition

Most of the pages in this family are one hypothesis each. This directory is the place where the choice of teacher is the hypothesis.

If you want to know whether a learned board evaluator can help, "learned from what?" is the question that matters most, and it is easy to answer accidentally by only ever trying one source. So the trainer exposes four:

• shape — fit the existing hand-written evaluation, the cheapest possible teacher, useful mainly as a wiring check and a speed baseline;
• oracle — fit the choices of a planner that has been shown the future, the strongest possible signal and an unusable policy;
• fitted — fit a target computed from the model's own bounded continuations, a self-improvement loop;
• contrastive — fit the gap between columns at one position rather than any column's absolute value, with a declared margin and temperature.

Keeping all four in one trainer with one encoder means the comparison between them is not confounded by four different implementations.

How it works

1. Fixed seed lanes. Three ranges are hard-coded and never moved: training (0x1d70…), calibration (0x5d70…) and validation (0x7d70…). The source comment states the reason plainly — the ranges stay fixed so that checkpoints trained at different times remain directly comparable.
2. Generate. Games are played on the training lane by the selected teacher. Every kind of randomness the trainer touches — reveals, exploration, shuffles, the fitted target's own futures — is drawn from its own labelled deterministic domain, so two runs of the same configuration produce the same data.
3. Encode. Sparse public board features plus next disc and rise phase.
4. Fit. Huber-loss regression with gradient clipping and Adam for value targets; smoothed classification for policy targets.
5. Use. A trained value model can be dropped in as the leaf of the sparse expectimax search or the rollout solver that the file imports, which is how the learned evaluation was actually put to work.

What happened

The one recorded outcome is a warning about where a learned evaluator helps: an early learned leaf improved a one-ply policy and made the stronger rollout policy worse. In other words, the model was adding something the weak policy lacked and subtracting something the strong policy already had — so measuring it against a weak baseline would have produced a positive result and a wrong conclusion.

No score, cohort or checkpoint is retained for this. The index labels it task-record only, and it is careful to reject only the configurations that were actually tried, not the workbench.

The technical record

The experiment index row reads: "General TypeScript value model … Trains sparse board/policy models from shape, oracle, fitted, or contrastive teachers with disjoint seed lanes. Rejected — task-record only for the tested configurations; early learned leaves helped one ply but hurt the stronger rollout policy."

A search of the ledger finds no protocol or result for value-model/train.ts, so there is no retained number on this page: no paired cohort, no gate, no checkpoint. The seed lanes, teacher modes, deterministic domains, loss functions and search integrations described above are read from the source and are repository-verified — evidence that the machinery exists and is disciplined, not evidence that anything it produced played well.

Note the qualifier the index chose: for the tested configurations. Four teachers, several targets and several search integrations are selectable here; the retained record covers one outcome.

What this taught us, and what is still open

The finding that survived is methodological: a learned component must be tested against the strongest baseline it would replace, not the weakest one it can beat. A leaf that improves one-ply play tells you almost nothing about a leaf inside a deep search, because the search may already be recovering the information the leaf supplies. That principle is visible in every later gate in this repository, which compare against fair depth-4 expectimax rather than against a convenient weaker policy.

What is still open here is most of the workbench. Three of the four teachers have no retained result at all, and the trainer is intact, deterministic and lane-disciplined. Reviving it would mean registering a theory and a frozen gate first — not rerunning it to see what happens.