Partially observable markov decision processes in robotics: A survey

M Lauri, D Hsu, J Pajarinen - IEEE Transactions on Robotics, 2022 - ieeexplore.ieee.org
Noisy sensing, imperfect control, and environment changes are defining characteristics of
many real-world robot tasks. The partially observable Markov decision process (POMDP) …

Model-based multi-agent reinforcement learning: Recent progress and prospects

X Wang, Z Zhang, W Zhang - arXiv preprint arXiv:2203.10603, 2022 - arxiv.org
Significant advances have recently been achieved in Multi-Agent Reinforcement Learning
(MARL) which tackles sequential decision-making problems involving multiple participants …

A survey of progress on cooperative multi-agent reinforcement learning in open environment

L Yuan, Z Zhang, L Li, C Guan, Y Yu - arXiv preprint arXiv:2312.01058, 2023 - arxiv.org
Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and
has made progress in various fields. Specifically, cooperative MARL focuses on training a …

Asynchronous actor-critic for multi-agent reinforcement learning

Y Xiao, W Tan, C Amato - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Synchronizing decisions across multiple agents in realistic settings is problematic since it
requires agents to wait for other agents to terminate and communicate about termination …

Modeling, replicating, and predicting human behavior: a survey

A Fuchs, A Passarella, M Conti - ACM Transactions on Autonomous and …, 2023 - dl.acm.org
Given the popular presupposition of human reasoning as the standard for learning and
decision making, there have been significant efforts and a growing trend in research to …

[HTML][HTML] Learning scalable and efficient communication policies for multi-robot collision avoidance

Á Serra-Gómez, H Zhu, B Brito, W Böhmer… - Autonomous …, 2023 - Springer
Decentralized multi-robot systems typically perform coordinated motion planning by
constantly broadcasting their intentions to avoid collisions. However, the risk of collision …

[HTML][HTML] Efficient and scalable reinforcement learning for large-scale network control

C Ma, A Li, Y Du, H Dong, Y Yang - Nature Machine Intelligence, 2024 - nature.com
The primary challenge in the development of large-scale artificial intelligence (AI) systems
lies in achieving scalable decision-making—extending the AI models while maintaining …

Centralized model and exploration policy for multi-agent RL

Q Zhang, C Lu, A Garg, J Foerster - arXiv preprint arXiv:2107.06434, 2021 - arxiv.org
Reinforcement learning (RL) in partially observable, fully cooperative multi-agent settings
(Dec-POMDPs) can in principle be used to address many real-world challenges such as …

Decentralized, unlabeled multi-agent navigation in obstacle-rich environments using graph neural networks

X Ji, H Li, Z Pan, X Gao, C Tu - 2021 IEEE/RSJ International …, 2021 - ieeexplore.ieee.org
We propose a decentralized, learning-based solution to the challenging problem of
unlabeled multi-agent navigation among obstacles, where robots need to simultaneously …

Learning pneumatic non-prehensile manipulation with a mobile blower

J Wu, X Sun, A Zeng, S Song… - IEEE Robotics and …, 2022 - ieeexplore.ieee.org
We investigate pneumatic non-prehensile manipulation (ie, blowing) as a means of
efficiently moving scattered objects into a target receptacle. Due to the chaotic nature of …