PulseAugur
实时 22:16:13

Mahjong RL simulator Mahjax achieves 2M steps/sec on GPUs

Researchers have developed Mahjax, a new GPU-accelerated simulator for the complex game of Riichi Mahjong, implemented in JAX. This tool is designed to facilitate reinforcement learning research, particularly for agents learning from scratch rather than relying on human play data. Mahjax achieves high throughput, processing up to 2 million steps per second on multiple GPUs, and has been validated for training agents to improve their performance. AI

影响 Enables large-scale reinforcement learning research for complex games, potentially leading to more general AI decision-making capabilities.

排序理由 The cluster describes a new research paper detailing a simulator for reinforcement learning.

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Soichiro Nishimori, Shinri Okano, Keigo Habara, Sotetsu Koyamada, Eason Yu, Masashi Sugiyama ·

    Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX

    arXiv:2605.20577v1 Announce Type: new Abstract: Riichi Mahjong is a multi-player, imperfect-information game characterized by stochasticity and high-dimensional state spaces. These attributes present a unique combination of challenges that mirror complex real-world decision-makin…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX

    Riichi Mahjong is a multi-player, imperfect-information game characterized by stochasticity and high-dimensional state spaces. These attributes present a unique combination of challenges that mirror complex real-world decision-making problems in reinforcement learning. While prio…