Skip to content

Manaka

CPU-first evaluator line built around incrementally updated sums. The native design avoids shogi-specific hand-crafted cross-features; separate KP/HalfKP experiments exist only as controls for measuring what those features buy.

Manaka's search is PUCT MCTS, not DLManaka's Gumbel search.

Read by topic

Design

  • Architecture — current shape grammar and evaluator structure
  • Network history — A–E measurements, later aggregation ideas, current switches
  • Structural critique — historical diagnosis, reconciled with later measurements
  • Search design — placeholder; current PUCT implementation is not yet documented separately
  • Inference — placeholder; architecture/benchmark pages currently cover the relevant path

Training and self-play

Measurement

Placeholder topics

Value-head decay, self-play plan, and improvement plan are reserved URLs without dedicated Manaka write-ups yet.

The old “loses to material counting” result describes an early v2 policy and is not the current-state summary. Later architecture measurements are the stronger reference.