FedKL: Tackling data heterogeneity in federated reinforcement learning by penalizing KL divergence
One of the fundamental issues for Federated Learning (FL) is data heterogeneity, which
causes accuracy degradation, slow convergence, and the communication bottleneck issue …
causes accuracy degradation, slow convergence, and the communication bottleneck issue …
Towards self-driving radios: Physical-layer control using deep reinforcement learning
Modern radios, such as 5G New Radio, feature a large set of physical-layer control knobs in
order to support an increasing number of communication scenarios spanning multiple use …
order to support an increasing number of communication scenarios spanning multiple use …
Cooperative heterogeneous deep reinforcement learning
Numerous deep reinforcement learning agents have been proposed, and each of them has
its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep …
its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep …
Improving sample efficiency of multi-agent reinforcement learning with non-expert policy for flocking control
Control algorithms of a multiagent system (MAS) have been applied to many Internet of
Things devices, such as unmanned aerial vehicles and autonomous underwater vehicles …
Things devices, such as unmanned aerial vehicles and autonomous underwater vehicles …
Icran: Intelligent control for self-driving ran based on deep reinforcement learning
AH Ahmed, A Elmokashfi - IEEE Transactions on Network and …, 2022 - ieeexplore.ieee.org
Mobile networks are increasingly expected to support use cases with diverse performance
expectations at a very high level of reliability. These expectations imply the need for …
expectations at a very high level of reliability. These expectations imply the need for …
Beyond conservatism: Diffusion policies in offline multi-agent reinforcement learning
We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent
Reinforcement Learning (MARL). Different from existing algorithms that rely mainly on …
Reinforcement Learning (MARL). Different from existing algorithms that rely mainly on …
Deep reinforcement learning for communication flow control in wireless mesh networks
Wireless mesh network (WMN) is one of the most promising technologies for Internet of
Things (IoT) applications because of its self-adaptive and self-organization nature. To meet …
Things (IoT) applications because of its self-adaptive and self-organization nature. To meet …
Sample-efficient multi-agent reinforcement learning with demonstrations for flocking control
Y Qiu, Y Zhan, Y Jin, J Wang… - 2022 IEEE 96th Vehicular …, 2022 - ieeexplore.ieee.org
Flocking control is a significant problem in multi-agent systems such as multi-agent
unmanned aerial vehicles and multi-agent autonomous underwater vehicles, which …
unmanned aerial vehicles and multi-agent autonomous underwater vehicles, which …
RayNet: A simulation platform for developing reinforcement learning-driven network protocols
L Giacomoni, B Benny, G Parisis - arXiv preprint arXiv:2302.04519, 2023 - arxiv.org
Reinforcement Learning (RL) has gained significant momentum in the development of
network protocols. However, RL-based protocols are still in their infancy, and substantial …
network protocols. However, RL-based protocols are still in their infancy, and substantial …
Darl1n: Distributed multi-agent reinforcement learning with one-hop neighbors
Multi-agent reinforcement learning (MARL) meth-ods face a curse of dimensionality in the
policy and value function representations as the number of agents increases. The …
policy and value function representations as the number of agents increases. The …