Is FISHER All You Need in The Multi-AUV Underwater Target Tracking Task?

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xie, Guanwen, Xu, Jingzehua, Zhang, Ziqi, Hou, Xiangwang, Ma, Dongfang, Zhang, Shuai, Ren, Yong, Niyato, Dusit
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908564240465920
author Xie, Guanwen
Xu, Jingzehua
Zhang, Ziqi
Hou, Xiangwang
Ma, Dongfang
Zhang, Shuai
Ren, Yong
Niyato, Dusit
author_facet Xie, Guanwen
Xu, Jingzehua
Zhang, Ziqi
Hou, Xiangwang
Ma, Dongfang
Zhang, Shuai
Ren, Yong
Niyato, Dusit
contents It is significant to employ multiple autonomous underwater vehicles (AUVs) to execute the underwater target tracking task collaboratively. However, it's pretty challenging to meet various prerequisites utilizing traditional control methods. Therefore, we propose an effective two-stage learning from demonstrations training framework, FISHER, to highlight the adaptability of reinforcement learning (RL) methods in the multi-AUV underwater target tracking task, while addressing its limitations such as extensive requirements for environmental interactions and the challenges in designing reward functions. The first stage utilizes imitation learning (IL) to realize policy improvement and generate offline datasets. To be specific, we introduce multi-agent discriminator-actor-critic based on improvements of the generative adversarial IL algorithm and multi-agent IL optimization objective derived from the Nash equilibrium condition. Then in the second stage, we develop multi-agent independent generalized decision transformer, which analyzes the latent representation to match the future states of high-quality samples rather than reward function, attaining further enhanced policies capable of handling various scenarios. Besides, we propose a simulation to simulation demonstration generation procedure to facilitate the generation of expert demonstrations in underwater environments, which capitalizes on traditional control methods and can easily accomplish the domain transfer to obtain demonstrations. Extensive simulation experiments from multiple scenarios showcase that FISHER possesses strong stability, multi-task performance and capability of generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03959
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Is FISHER All You Need in The Multi-AUV Underwater Target Tracking Task?
Xie, Guanwen
Xu, Jingzehua
Zhang, Ziqi
Hou, Xiangwang
Ma, Dongfang
Zhang, Shuai
Ren, Yong
Niyato, Dusit
Robotics
Systems and Control
It is significant to employ multiple autonomous underwater vehicles (AUVs) to execute the underwater target tracking task collaboratively. However, it's pretty challenging to meet various prerequisites utilizing traditional control methods. Therefore, we propose an effective two-stage learning from demonstrations training framework, FISHER, to highlight the adaptability of reinforcement learning (RL) methods in the multi-AUV underwater target tracking task, while addressing its limitations such as extensive requirements for environmental interactions and the challenges in designing reward functions. The first stage utilizes imitation learning (IL) to realize policy improvement and generate offline datasets. To be specific, we introduce multi-agent discriminator-actor-critic based on improvements of the generative adversarial IL algorithm and multi-agent IL optimization objective derived from the Nash equilibrium condition. Then in the second stage, we develop multi-agent independent generalized decision transformer, which analyzes the latent representation to match the future states of high-quality samples rather than reward function, attaining further enhanced policies capable of handling various scenarios. Besides, we propose a simulation to simulation demonstration generation procedure to facilitate the generation of expert demonstrations in underwater environments, which capitalizes on traditional control methods and can easily accomplish the domain transfer to obtain demonstrations. Extensive simulation experiments from multiple scenarios showcase that FISHER possesses strong stability, multi-task performance and capability of generalization.
title Is FISHER All You Need in The Multi-AUV Underwater Target Tracking Task?
topic Robotics
Systems and Control
url https://arxiv.org/abs/2412.03959