Metraipolis › archive › dc_7d12d4280156
PokaiTrainer: Scaling Equilibrium Search to Competitive Pokémon VGC — arXiv:2608.29197
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29197
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:47:33.771Z
- SHA-256 of the archived text
bcfc3cd1da9e1abca5cef99737c30a3253c21083dcb5ec96b3c91ba529f60fbb- Stable URL of this page
https://metraipolis.com/documento/dc_7d12d4280156
How to cite
PokaiTrainer: Scaling Equilibrium Search to Competitive Pokémon VGC — arXiv:2608.29197 — arXiv (en), https://arxiv.org/abs/2608.29197 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7d12d4280156 (Metraipolis archive dc_7d12d4280156, sha256 bcfc3cd1da9e1abca5cef99737c30a3253c21083dcb5ec96b3c91ba529f60fbb)
BibTeX
@misc{dc7d12d4280156,
title = {PokaiTrainer: Scaling Equilibrium Search to Competitive Pokémon VGC — arXiv:2608.29197},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29197},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7d12d4280156; sha256 bcfc3cd1da9e1abca5cef99737c30a3253c21083dcb5ec96b3c91ba529f60fbb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29197. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Decision-time equilibrium search carried poker to superhuman play, but it has so far relied on tractable subgames: a handful of actions per decision, chance confined to card deals, one player moving at a time. Competitive Pokémon in its official doubles format (VGC) breaks all three assumptions at once. Both players act simultaneously from joint menus in the hundreds, each joint action resolves to hundreds of stochastic outcomes, and the opponent's reserves and stat allocations are hidden. No prior Pokémon agent performs equilibrium search, and whether it scales to this regime was open; we show that it does, and report what it took. PokaiEngine, our Rust battle engine, enumerates a joint action's full weighted outcome distribution in one pass, at ${\sim}99\%$ parity with Pokémon Showdown and a fraction of the cost of sampling it. PokaiTrainer adapts Student of Games to this scale and trains it by self-play over hundreds of human teams. Each decision is solved by counterfactual regret minimization as a Bayesian matrix game over public belief states, subgames grow under an explicit compute budget, and value targets are harvested from the interior of every solve and grounded by realized outcomes. The strength is in the search. The network's policy alone loses even to a shallow heuristic search. PokaiTrainer is, to our knowledge, the first VGC agent rated on the live Showdown ladder. Under open team sheets it wins 59% of 150 best-of-three sets against a human field averaging ${\sim}1320$ Elo, holds a 1350-1400 Elo band, and at its peak reached 1492 Elo, entering the format's top 500.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2608.29197 — 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 2026-10-17T07:28:26.728Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).