用博弈搜索打造能打对战赛的宝可梦智能体，胜率超五成。
PokaiTrainer: Scaling Belief-State Search to Competitive Pokémon VGC
- 将博弈论搜索扩展到同时行动、海量选择、随机结果的复杂对战环境。
- 在真实对战平台胜率达59%，稳定在1350-1400分段。
- 适合研究强化学习与博弈论结合的玩家和开发者参考。
决策时均衡搜索曾让扑克达到超人水平，但此前依赖可处理的子博弈：每次决策仅少数动作、随机性限于发牌、轮流行动。而官方双打对战（VGC）同时打破这三项假设：双方从数百个联合动作中同步选择，每个联合动作引发数百种随机结果，对手的储备与属性分配完全隐藏。我们致力于构建强力的VGC智能体，并报告实现过程。PokaiEngine是用Rust编写的战斗引擎，可在一次遍历中计算联合动作的完整加权结果分布，与Pokémon Showdown相比误差约1%，成本仅为采样的几分之一。在此基础上，PokaiTrainer将‘学生游戏’方法适配至该规模，将每个决策视为基于公开信念状态的贝叶斯矩阵博弈，并在显式算力预算下动态扩展子博弈。在Showdown实时三局两胜排位中，该智能体在150场对战中击败平均约1320分的真人选手，胜率59%。其表现稳定在1350-1400分区间，巅峰时一度进入全服前500名。
原文摘要 · Abstract (English)
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. We set out to build a strong VGC agent and report what that 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. On top of the engine, PokaiTrainer adapts Student of Games to this scale, solving every decision as a Bayesian matrix game over public belief states and growing subgames under an explicit compute budget. On the live Showdown best-of-three ladder, the agent wins 59% of 150 sets against a human field averaging ${\sim}1320$ Elo. It settles into a 1350-1400 Elo band, and at its peak briefly entered the format's top 500.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。