Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: O'Connor, Jim, Gezgin, Derin, Parker, Gary B.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913983238242304
author O'Connor, Jim
Gezgin, Derin
Parker, Gary B.
author_facet O'Connor, Jim
Gezgin, Derin
Parker, Gary B.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07522
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong
O'Connor, Jim
Gezgin, Derin
Parker, Gary B.
Neural and Evolutionary Computing
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.
title Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2508.07522