# Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong

arXiv: https://arxiv.org/abs/2508.07522 · HTML: https://mlsanity.com/paper/2508.07522/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods.
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Placed in

- Deep reinforcement learning methods / [RL for games and combinatorial optimization](https://mlsanity.com/deeprl/rl-for-games-and-combinatorial-optimization/)

## Builds on (most cited first, 9 of 9)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [The Hanabi Challenge: A New Frontier for AI Research](https://mlsanity.com/paper/1902.00506/) (2019)
- [Suphx: Mastering Mahjong with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.13590/) (2020)
- [Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning](https://mlsanity.com/paper/2303.17503/) (2023)
- [Depth-Limited Solving for Imperfect-Information Games](https://mlsanity.com/paper/1805.08195/) (2018)
- [Building a Computer Mahjong Player via Deep Convolutional Neural Networks](https://mlsanity.com/paper/1906.02146/) (2019)

## Abstract (arXiv)

We present Evo-Sparrow, a deep learning-based agent for AI decision-making in Sparrow Mahjong, trained by optimizing Long Short-Term Memory (LSTM) networks using Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Our model evaluates board states and optimizes decision policies in a non-deterministic, partially observable game environment. Empirical analysis conducted over a significant number of simulations demonstrates that our model outperforms both random and rule-based agents, and achieves performance comparable to a Proximal Policy Optimization (PPO) baseline, indicating strong strategic play and robust policy quality. By combining deep learning with evolutionary optimization, our approach provides a computationally effective alternative to traditional reinforcement learning and gradient-based optimization methods. This research contributes to the broader field of AI game playing, demonstrating the viability of hybrid learning strategies for complex stochastic games. These findings also offer potential applications in adaptive decision-making and strategic AI development beyond Sparrow Mahjong.