Mahjax provides a GPU-accelerated JAX implementation of Riichi Mahjong achieving up to 2 million steps per second and enabling effective tabula rasa reinforcement learning.
A general reinforcement learning algorithm that masters chess, shogi, and go through self-play,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX
Mahjax provides a GPU-accelerated JAX implementation of Riichi Mahjong achieving up to 2 million steps per second and enabling effective tabula rasa reinforcement learning.