Ldsa: Learning dynamic subtask assignment in cooperative multi-agent reinforcement learning

M Yang, J Zhao, X Hu, W Zhou… - Advances in Neural …, 2022 - proceedings.neurips.cc
Cooperative multi-agent reinforcement learning (MARL) has made prominent progress in
recent years. For training efficiency and scalability, most of the MARL algorithms make all …

Achieving fair-effective communications and robustness in underwater acoustic sensor networks: A semi-cooperative approach

Y Gou, T Zhang, J Liu, T Yang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
This paper investigates the fair-effective communication and robustness in imperfect and
energy-constrained underwater acoustic sensor networks (IC-UASNs). Specifically, we …

Ma2cl: Masked attentive contrastive learning for multi-agent reinforcement learning

H Song, M Feng, W Zhou, H Li - arxiv preprint arxiv:2306.02006, 2023 - arxiv.org
Recent approaches have utilized self-supervised auxiliary tasks as representation learning
to improve the performance and sample efficiency of vision-based reinforcement learning …

Joint link scheduling and power allocation in imperfect and energy-constrained underwater wireless sensor networks

T Zhang, Y Gou, J Liu, S Song… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Underwater wireless sensor networks (UWSNs) stand as promising technologies facilitating
diverse underwater applications. However, the major design issues of the considered …

Petri Nets and hierarchical reinforcement learning for personalized student assistance in serious games

R Hare, Y Tang - … on Cyber-Physical Social Intelligence (ICCSI), 2022 - ieeexplore.ieee.org
Adaptive serious games offer a new frontier for education, especially in complex topics.
However, optimal methods for in-game adaptation are still being explored to address …

Embedding multi-agent reinforcement learning into behavior trees with unexpected interruptions

X Li, Y Li, J Zhang, X Xu, D Liu - Complex & Intelligent Systems, 2024 - Springer
Behavior trees have attracted great interest in computer games and robotic applications.
However, it lacks the learning ability for dynamic environments. Previous works combining …

Enhancing low-resource cross-lingual summarization from noisy data with fine-grained reinforcement learning

Y Huang, H Gu, Z Yu, Y Gao, T Pan, J Xu - Frontiers of Information …, 2024 - Springer
Cross-lingual summarization (CLS) is the task of generating a summary in a target language
from a document in a source language. Recently, end-to-end CLS models have achieved …

[PDF][PDF] Robust Multi-Agent Reinforcement Learning for Autonomous Vehicle in Noisy Highway Environments

L Lin, X Nie, J Hou - The 16th Asian Conference on …, 2024 - raw.githubusercontent.com
The field of research on multi-agent reinforcement learning (MARL) algorithms in selfdriving
vehicles is rapidly expanding in mixed-traffic scenarios where autonomous vehicles (AVs) …

Study on the Modeling of Navigator Agent for Marine Engine Management Simulation System

L Chen, X Peng, C Guan, H Chen - International Conference on Marine …, 2023 - Springer
Modeling and simulation of the marine engine system is a highly complex system that
involves many components such as cabin equipment, marine engineers, navigators, and …

基于细粒度**化学**增**噪声数据的低资源跨语言摘要

Y HUANG, H GU, Z YU, Y GAO, T PAN, J XU… - Frontiers, 2024 - jzus.zju.edu.cn
跨语言摘要是从源语言文档生成目标语言摘要的任务. 最**, 端到端跨语言摘要模型通过使用大
规模, 高质量数据集取得令人瞩目的结果, 这些数据集通常是通过将单语摘要语料库翻译成跨 …