Ensuring threshold AoI for UAV-assisted mobile crowdsensing by multi-agent deep reinforcement learning with transformer
Unmanned aerial vehicle (UAV) crowdsensing (UCS) is an emerging data collection
paradigm to provide reliable and high quality urban sensing services, with age-of …
paradigm to provide reliable and high quality urban sensing services, with age-of …
DePAint: a decentralized safe multi-agent reinforcement learning algorithm considering peak and average constraints
The domain of safe multi-agent reinforcement learning (MARL), despite its potential
applications in areas ranging from drone delivery and vehicle automation to the …
applications in areas ranging from drone delivery and vehicle automation to the …
Decentralized natural policy gradient with variance reduction for collaborative multi-agent reinforcement learning
This paper studies a policy optimization problem arising from collaborative multi-agent
reinforcement learning in a decentralized setting where agents communicate with their …
reinforcement learning in a decentralized setting where agents communicate with their …
Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
In Federated Reinforcement Learning (FRL), agents aim to collaboratively learn a common
task, while each agent is acting in its local environment without exchanging raw trajectories …
task, while each agent is acting in its local environment without exchanging raw trajectories …
Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning
Multi-task reinforcement learning (RL) aims to find a single policy that effectively solves
multiple tasks at the same time. This paper presents a constrained formulation for multi-task …
multiple tasks at the same time. This paper presents a constrained formulation for multi-task …
Decentralized multi-task reinforcement learning policy gradient method with momentum over networks
S Junru, W Qiong, L Muhua, J Zhihang, Z Ruijuan… - Applied …, 2023 - Springer
To find the optimal policy quickly for reinforcement learning problems, policy gradient (PG)
method is very effective, it parameters the policy and updates policy parameter directly …
method is very effective, it parameters the policy and updates policy parameter directly …
A distributed adaptive policy gradient method based on momentum for multi-agent reinforcement learning
J Shi, X Wang, M Zhang, M Liu, J Zhu, Q Wu - Complex & Intelligent …, 2024 - Springer
Policy Gradient (PG) method is one of the most popular algorithms in Reinforcement
Learning (RL). However, distributed adaptive variants of PG are rarely studied in multi …
Learning (RL). However, distributed adaptive variants of PG are rarely studied in multi …