Enhanced LSTM-DQN algorithm for a two-player zero-sum game in three-dimensional space

DOI10.1049/CTH2.12677MaRDI QIDQ6875474zbMATH OpenFDO

Authors Bo Lü, Le Ru, Mao-long Lv, Shiguang Hu, Hongguo Zhang, Zi-Long Zhao

Publication date 13 January 2026

Published in IET Control Theory \& Applications (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial 4.0 International

Full work available at URL https://doi.org/10.1049/CTH2.12677

zbMATH Keywords

deep reinforcement learninghindsight experience replaylong short term memory-deep Q-learningmanoeuvre decision-makingthree-dimensional spacetwo-player zero-sum game

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) 2-person games (91A05) Noncooperative games (91A10) Algorithmic game theory and complexity (91A68)

Cites work

• 10.1162/1532443041827880
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• A survey of solution techniques for the partially observed Markov decision process

Cited in

(1)

• Collaborative decision-making for UAV swarm confrontation based on reinforcement learning

This page was built for publication: Enhanced LSTM-DQN algorithm for a two-player zero-sum game in three-dimensional space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6875474)