The Application of Co-evolutionary Genetic Programming and TD(1) Reinforcement Learning in Large-Scale Strategy Game VCMI

被引：3

作者：

Wilisowski, Lukasz ^{[1
]}

Drezewski, Rafal ^{[1
]}

机构：

[1] AGH Univ Sci & Technol, Dept Comp Sci, Krakow, Poland

来源：

AGENT AND MULTI-AGENT SYSTEMS: TECHNOLOGIES AND APPLICATIONS | 2015年 / 38卷

关键词：

Genetic programming; Neural networks; Strategy games; CARLO TREE-SEARCH;

D O I：

10.1007/978-3-319-19728-9_7

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

VCMI is a new, open-source project that could become one of the biggest testing platform for modern AI algorithms in the future. Its complex environment and turn-based gameplay make it a perfect system for any AI driven solution. It also has a large community of active players which improves the testability of target algorithms. This paper explores VCMI's environment and tries to assess its complexity by providing a base solution for battle handling problem using two global optimization algorithms: Co-Evolution of Genetic Programming Trees and TD(1) algorithm with Back Propagation neural network. Both algorithms have been used in VCMI to evolve battle strategies through a fully autonomous learning process. Finally, the obtained strategies have been tested against existing solutions and compared with players' best tactics.

引用

页码：81 / 93

页数：13

共 50 条

[11] A Mixed-Game and Co-evolutionary Genetic Programming Agent-Based Model of Financial Contagion
Liu, Fang
Serguieva, Antoaneta
Date, Paresh
2010 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2010,
[12] A Cooperative Co-evolutionary Algorithm for solving Large-Scale Constrained Problems with Interaction Detection
Blanchard, Julien
Beauthier, Charlotte
Carletti, Timoteo
PROCEEDINGS OF THE 2017 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'17), 2017, : 697 - 704
[13] A Cooperative Co-Evolutionary Approach to Large-Scale Multisource Water Distribution Network Optimization
Chen, Wei-Neng
Jia, Ya-Hui
Zhao, Feng
Luo, Xiao-Nan
Jia, Xing-Dong
Zhang, Jun
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2019, 23 (05) : 842 - 857
[14] Effective Decomposition of Large-Scale Separable Continuous Functions for Cooperative Co-evolutionary Algorithms
Omidvar, Mohammad Nabi
Mei, Yi
Li, Xiaodong
2014 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2014, : 1305 - 1312
[15] Cooperative Co-evolutionary Teaching-Learning Based Algorithm with a Modified Exploration Strategy for Large Scale Global Optimization
Biswas, Subhodip
Kundu, Souvik
Bose, Digbalay
Das, Swagatam
SWARM, EVOLUTIONARY, AND MEMETIC COMPUTING, (SEMCCO 2012), 2012, 7677 : 467 - 475
[16] Constructing large-scale genetic maps using an evolutionary strategy algorithm
Mester, D
Ronin, Y
Minkov, D
Nevo, E
Korol, A
GENETICS, 2003, 165 (04) : 2269 - 2282
[17] A Novel Quantum Cooperative Co-evolutionary Algorithm for Large-Scale Minimum Attribute Reduction Optimization
Ding, Weiping
Shi, Quan
Chen, Senbo
Guan, Zhijin
Wang, Jiandong
2013 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DATA MINING (CIDM), 2013, : 280 - 286
[18] NEAT for Large-Scale Reinforcement Learning through Evolutionary Feature Learning and Policy Gradient Search
Peng, Yiming
Chen, Gang
Singh, Harman
Zhang, Mengjie
GECCO'18: PROCEEDINGS OF THE 2018 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2018, : 490 - 497
[19] A co-evolutionary algorithm based on sparsity clustering for sparse large-scale multi-objective optimization
Zhang, Yajie
Wu, Chengming
Tian, Ye
Zhang, Xingyi
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 133
[20] Graph-based strategy evaluation for large-scale multiagent reinforcement learning
Sun, Yiyun
Liu, Meiqin
Zhang, Senlin
Zheng, Ronghao
Dong, Shanling
SCIENCE CHINA-INFORMATION SCIENCES, 2025, 68 (08)

← 1 2 3 4 5 →