Centralized Reinforcement Learning

Centralized reinforcement learning (CRL) addresses the challenges of coordinating multiple agents or components within a system to achieve a common goal, overcoming limitations of fully decentralized approaches. Current research focuses on developing efficient CRL algorithms, including variations of deep Q-networks and actor-critic methods, often tailored to specific applications like traffic control and wireless network optimization. This approach is significant because it enables effective control in complex, large-scale systems where decentralized methods struggle, leading to improved performance and resource management in various domains.

Papers

October 14, 2024

STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack
Naman Gupta, Shashank Kirtania, Priyanshu Gupta, Krishna Kariya, Sumit Gulwani, Arun Iyer, Suresh Parthasarathy, Arjun Radhakrishna, Sriram K. Rajamani, Gustavo Soares
Retrieval Augmented Generation Human Feedback Knowledge Editing Textual Structure Feed Ranking Centralized Reinforcement Learning

August 20, 2024

Knowledge Sharing and Transfer via Centralized Reward Agent for Multi-Task Reinforcement Learning
Haozhe Ma, Zhengding Luo, Thanh Vinh Vo, Kuankuan Sima, Tze-Yun Leong
Reinforcement Learning Formality Transfer Reward Shaping Multi Task Reinforcement Learning Knowledge Sharing Centralized Reinforcement Learning

May 3, 2024

Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach
Anton Plaksin, Vitaly Kalev
New Framework Multi Agent Reinforcement Learning Constructive Approach Robust Reinforcement Learning Differential Game Centralized Reinforcement Learning

January 28, 2024

A Centralized Reinforcement Learning Framework for Adaptive Clustering with Low Control Overhead in IoT Networks
F. Fernando Jurado-Lasso, J. F. Jurado, Xenofon Fafoutis
Internet of Thing Network Adaptive Clustering Centralized Reinforcement Learning

June 5, 2023

A Novel Multi-Agent Deep RL Approach for Traffic Signal Control
Shijie Wang, Shangbo Wang
Multi Agent Deep Reinforcement Learning Traffic Signal Control DQN Agent Adaptive Traffic Signal Control Centralized Reinforcement Learning

April 20, 2023

SocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal Control
Harsh Goel, Yifeng Zhang, Mehul Damani, Guillaume Sartoretti
Reinforcement Learning Multi Agent Reinforcement Learning Adaptive Traffic Signal Control Cooperative Intelligent Centralized Reinforcement Learning

March 21, 2023

Large-Scale Traffic Signal Control Using Constrained Network Partition and Adaptive Deep Reinforcement Learning
Hankang Gu, Shangbo Wang, Xiaoguang Ma, Dongyao Jia, Guoqiang Mao, Eng Gee Lim, Cheuk Pong Ryan Wong
Traffic Network Graph Partitioning Decentralized Reinforcement Learning Centralized Reinforcement Learning

January 2, 2023

Large-Scale Traffic Signal Control by a Nash Deep Q-network Approach
Yuli. Zhang, Shangbo. Wang, Ruiyuan. Jiang
Reinforcement Learning Multi Agent Reinforcement Learning Multi Agent Traffic Model Centralized Reinforcement Learning

December 7, 2021

Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks
Peyman Tehrani, Francesco Restuccia, Marco Levorato
Reinforcement Learning Deep Neural Network Deep Reinforcement Learning Federated Reinforcement Learning NextG Wireless Network Centralized Reinforcement Learning Distributed Control

Centralized Reinforcement Learning

Papers

STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack

Knowledge Sharing and Transfer via Centralized Reward Agent for Multi-Task Reinforcement Learning

Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach

A Centralized Reinforcement Learning Framework for Adaptive Clustering with Low Control Overhead in IoT Networks

A Novel Multi-Agent Deep RL Approach for Traffic Signal Control

SocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal Control

Large-Scale Traffic Signal Control Using Constrained Network Partition and Adaptive Deep Reinforcement Learning

Large-Scale Traffic Signal Control by a Nash Deep Q-network Approach

Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks