Metraipolis › archive › dc_d250386e710b

OpenBlock: Constructive and Verified Content Generation for Adaptive Tile-Matching Games — arXiv:2609.22177

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22177
License (as archived)
CC0-1.0
Archived
2026-10-09T06:58:07.209Z
SHA-256 of the archived text
640592d04eed83a10eab347938c2d4c78730de8d2b29ced4895de54e732a9c85
Stable URL of this page
https://metraipolis.com/documento/dc_d250386e710b

How to cite

OpenBlock: Constructive and Verified Content Generation for Adaptive Tile-Matching Games — arXiv:2609.22177 — arXiv (en), https://arxiv.org/abs/2609.22177 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d250386e710b (Metraipolis archive dc_d250386e710b, sha256 640592d04eed83a10eab347938c2d4c78730de8d2b29ced4895de54e732a9c85)
BibTeX
@misc{dcd250386e710b,
  title = {OpenBlock: Constructive and Verified Content Generation for Adaptive Tile-Matching Games — arXiv:2609.22177},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22177},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d250386e710b; sha256 640592d04eed83a10eab347938c2d4c78730de8d2b29ced4895de54e732a9c85},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22177. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tile-matching puzzle games serve hundreds of millions of players, yet the content-generation algorithms that decide which pieces to present at each turn remain proprietary, and no open platform exists for studying adaptive difficulty in this genre. We present an adaptive tile-matching platform whose central algorithmic contribution is a dual-track content-generation architecture: a deterministic rule-based generator that is always available, and an optional learned generator, both subject to a common verification gate that establishes, by exhaustive sequential-placement search, that every delivered piece set is fully placeable so the learned track can never degrade the constructive-feasibility guarantee of the rule track. A self-play reinforcement-learning placement agent, supervised by auxiliary tasks that expose per-shape placeability to shared representations, is used to diagnose the game's dominant failure mode: at high board fill, long-bar pieces lose the majority of their legal placements. Across 234,000+ self-play episodes the agent reaches a 35.6\% win rate (median score 4,200), and controlled simulation shows that at board fill rates of 70--75\%, 33--56\% of long-bar pieces have no legal placement, while spawn difficulty distributions are statistically indistinguishable between won and lost games---evidence that board-state degeneration, not content difficulty, drives late-game failure. Head-to-head ablations show that per-shape placeability supervision---not aggregate difficulty features---drives the representation gain, and a 14-day online gray rollout (48,000 players; sample-ratio verified, CUPED-adjusted) lifts day-1 retention by 1.8 percentage points and session duration by 7\% over the rule track alone, quantifying the neural track's asymmetric upside in live play.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-22 in cs.GT).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2609.22177 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:52:12.766Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).