Dynamic-layer transformer-based reinforcement learning for observation-constrained multi-agent roundup scenarios [PDF]
Scientific ReportsTo address the challenge of cooperative roundup of maneuvering targets under limited perception, this paper proposes TransMARL, a transformer-based multi-agent reinforcement learning framework for observation-constrained coordination. The roundup task is
Xizhao Li, Ning Xu, Qingjia Chi, Hu Chen
doaj +2 more sources
Faster algorithm and sharper analysis for constrained Markov decision process. [PDF]
Oper Res LetLi T +5 more
europepmc +2 more sources
Controllable Summarization with Constrained Markov Decision Process
Transactions of the Association for Computational Linguistics, 2021 We study controllable text summarization, which allows users to gain control on a particular attribute (e.g., length limit) of the generated summaries. In this work, we propose a novel training framework based on Constrained Markov Decision Process (CMDP)
Hou Pong Chan, Lu Wang, Irwin King
doaj +1 more source
Wireless Downlink Scheduling with Deadline Constraint for Realistic Channel Observation Environment [PDF]
Jisuanji kexue, 2021 Deadline-constrained wireless downlink transmissions,which have been widely used for a variety of real-time communication services that are related to the national economy and the people's livelihood,require each packet to be delivered in an ultra ...
ZHANG Fan, GONG Ao-yu, DENG Lei, LIU Fang, LIN Yan, ZHANG Yi-jin
doaj +1 more source
Optimizing Age Penalty in Time-Varying Networks with Markovian and Error-Prone Channel State
Entropy, 2021 In this paper, we consider a scenario where the base station (BS) collects time-sensitive data from multiple sensors through time-varying and error-prone channels.
Yuchao Chen +3 more
doaj +1 more source
A space of goals: the cognitive geometry of informationally bounded agents
Royal Society Open Science, 2022 Traditionally, Euclidean geometry is treated by scientists as a priori and objective. However, when we take the position of an agent, the problem of selecting a best route should also factor in the abilities of the agent, its embodiment and particularly ...
Karen Archer +3 more
doaj +1 more source
Frontiers in Neurorobotics, 2023 A system with multiple cooperating unmanned aerial vehicles (multi-UAVs) can use its advantages to accomplish complicated tasks. Recent developments in deep reinforcement learning (DRL) offer good prospects for decision-making for multi-UAV systems ...
Longfei Yue +3 more
doaj +1 more source
Deep Reinforcement Learning Under Signal Temporal Logic Constraints Using Lagrangian Relaxation
IEEE Access, 2022 Deep reinforcement learning (DRL) has attracted much attention as an approach to solve optimal control problems without mathematical models of systems. On the other hand, in general, constraints may be imposed on optimal control problems.
Junya Ikemoto, Toshimitsu Ushio
doaj +1 more source
Adaptive Virtual Resource Allocation in 5G Network Slicing Using Constrained Markov Decision Process
IEEE Access, 2018 Network virtualization technology is generally envisaged as a promising technology to consequently satisfy various types of service requirements. On the other hand, non-orthogonal multiple access (NOMA) technology has the potential to significantly ...
Lun Tang +4 more
doaj +1 more source
Dynamic Virtual Resource Allocation for 5G and Beyond Network Slicing
IEEE Open Journal of Vehicular Technology, 2020 The fifth generation and beyond wireless communication will support vastly heterogeneous services and user demands such as massive connection, low latency and high transmission rate.
Fei Song +5 more
doaj +1 more source