A CMA-ES-optimized LSTM agent for Sparrow Mahjong is claimed to beat random and rule-based agents and match a PPO baseline, but the provided manuscript contains no verifiable experiments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong
A CMA-ES-optimized LSTM agent for Sparrow Mahjong is claimed to beat random and rule-based agents and match a PPO baseline, but the provided manuscript contains no verifiable experiments.