Adaptive Genomic Evolution of Neural Network Topologies (AGENT) for State-to-Action Mapping in Autonomous Agents

被引:0
|
作者
Behjat, Amir [1 ]
Chidambaran, Sharat [1 ]
Chowdhury, Souma [1 ]
机构
[1] SUNY Buffalo, Dept Mech & Aerosp Engn, Buffalo, NY 14260 USA
关键词
NEUROEVOLUTION;
D O I
10.1109/icra.2019.8793613
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Neuroevolution is a process of training neural networks (NN) through an evolutionary algorithm, usually to serve as a state-to-action mapping model in control or reinforcement learning-type problems. This paper builds on the Neuro Evolution of Augmented Topologies (NEAT) formalism that allows designing topology and weight evolving NNs. Fundamental advancements are made to the neuroevolution process to address premature stagnation and convergence issues, central among which is the incorporation of automated mechanisms to control the population diversity and average fitness improvement within the neuroevolution process. Insights into the performance and efficiency of the new algorithm is obtained by evaluating it on three benchmark problems from the Open AI platform and an Unmanned Aerial Vehicle (UAV) collision avoidance problem.
引用
收藏
页码:9638 / 9644
页数:7
相关论文
共 11 条
  • [1] MULTI-CRITERIA EVOLUTION OF NEURAL NETWORK TOPOLOGIES: BALANCING EXPERIENCE AND PERFORMANCE IN AUTONOMOUS SYSTEMS
    Chidambaran, Sharat
    Behjat, Amir
    Chowdhury, Souma
    PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, 2018, VOL 2B, 2018,
  • [2] Adaptive Neural Network Tracking Control of Multi-agent Systems with State Constraints
    Li, Dongyu
    Ma, Guangfu
    Li, Chuangjiang
    Zhang, Wei
    He, Wei
    2017 CHINESE AUTOMATION CONGRESS (CAC), 2017, : 201 - 205
  • [3] Neural-Network-Based Predefined-Time Adaptive Consensus in Nonlinear Multi-Agent Systems With Switching Topologies
    Zhu, Yanzheng
    Wang, Zuo
    Liang, Hongjing
    Ahn, Choon Ki
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (07) : 9995 - 10005
  • [4] Neural-network-based adaptive quasi-consensus of nonlinear multi-agent systems with communication constrains and switching topologies
    Li, Hongjie
    Zhang, Jingjun
    Jing, Liu
    Ying, Wang
    NONLINEAR ANALYSIS-HYBRID SYSTEMS, 2020, 35
  • [5] Autonomous detection of myocarditis based on the fusion of improved quantum genetic algorithm and adaptive differential evolution optimization back propagation neural network
    Wu, Lei
    Guo, Shuli
    Han, Lina
    Song, Xiaowei
    Zhao, Zhilei
    Cekderi, Anil Baris
    HEALTH INFORMATION SCIENCE AND SYSTEMS, 2023, 11 (01)
  • [6] Autonomous detection of myocarditis based on the fusion of improved quantum genetic algorithm and adaptive differential evolution optimization back propagation neural network
    Lei Wu
    Shuli Guo
    Lina Han
    Xiaowei Song
    Zhilei Zhao
    Anil Baris Cekderi
    Health Information Science and Systems, 11
  • [7] Adaptive neural network-based practical fixed-time consensus tracking for second-order nonlinear multi-agent systems with switching topologies
    Dong, Yan
    Lu, Weihua
    Chen, Junwei
    Cao, Jinde
    Xu, Shunlin
    INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2024, 34 (12) : 8442 - 8464
  • [8] Adaptive Neural Network Control for Nonlinear Multi-Agent Systems With Actuator Faults and Asymmetric Time-Varying State Constraints
    Dong, Guowei
    Xu, Peitong
    Li, Ke-Wen
    INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2025,
  • [9] Adaptive bounded neural network control for coordinated path-following of networked underactuated autonomous surface vehicles under time-varying state-dependent cyber-attack
    Gu, Nan
    Wang, Dan
    Peng, Zhouhua
    Liu, Lu
    ISA TRANSACTIONS, 2020, 104 : 212 - 221
  • [10] Bipartite-tracking quasi-consensus of nonlinear uncertain multi-agent systems: neural network-based adaptive state-constraint impulsive control approach
    Xu, Ziqiang
    Li, Yun
    Zhan, Xisheng
    Yan, Huaicheng
    NONLINEAR DYNAMICS, 2023, 111 (13) : 12143 - 12159