AILGMay 20

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

arXiv:2605.2057771.8
AI Analysis

Provides a high-throughput environment for training RL agents in a complex imperfect-information game, facilitating research into learning without human data.

Mahjax is a GPU-accelerated Riichi Mahjong simulator in JAX that achieves up to 2 million steps per second on eight A100 GPUs, enabling tabula rasa reinforcement learning from scratch.

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 prior research has heavily relied on supervised learning from human play logs to pre-train the policy, algorithms capable of learning \textit{tabula rasa} (from scratch) offer greater potential for general applicability, as evidenced by the AlphaZero lineage. To facilitate such research, we introduce \textbf{Mahjax}, a fully vectorized Riichi Mahjong environment implemented in JAX to enable large-scale rollout parallelization on Graphics Processing Units (GPUs). We also provide a high-quality visualization tool to streamline debugging and interaction with trained agents. Experimental results demonstrate that Mahjax achieves throughputs of up to \textbf{2 million} and \textbf{1 million steps per second} on eight NVIDIA A100 GPUs under the no-red and red rules, respectively. Furthermore, we validate the environment's utility for reinforcement learning by showing that agents can be trained effectively to improve their rank against baseline policies.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes