Soft QMIX

Soft QMIX represents advancements in multi-agent reinforcement learning (MARL), aiming to improve the exploration and efficiency of cooperative agents by incorporating maximum entropy principles into the QMIX architecture. Current research focuses on enhancing QMIX's robustness to noise and adversarial attacks, improving its convergence speed through techniques like periodic parameter sharing, and addressing challenges in value function decomposition for better credit assignment among agents. These improvements have significant implications for various applications, including resource allocation in massive machine-type communication and robust decision-making in complex environments.

Papers

July 1, 2024

RegMix: Data Mixture as Regression for Language Model Pre-training
Qian Liu, Xiaosen Zheng, Niklas Muennighoff, Guangtao Zeng, Longxu Dou, Tianyu Pang, Jing Jiang, Min Lin
Large Language Model Language Model Novel Regression Data Mixture Soft QMIX

June 23, 2024

VICatMix: variational Bayesian clustering and variable selection for discrete biomedical data
Paul D. W. Kirk, Jackie Rao
High Dimensional Variational Inference Sequential Data Variable Selection Cancer Subtyping Soft QMIX Agglomerative Hierarchical Clustering Variational Mixture

June 20, 2024

Soft-QMIX: Integrating Maximum Entropy For Monotonic Value Function Factorization
Wentse Chen, Shiyu Huang, Jeff Schneider
Multi Agent Reinforcement Learning Maximum Entropy Deterministic Policy Maximum Entropy Reinforcement Learning Value Function Factorization Soft QMIX

April 8, 2024

QMix: Quality-aware Learning with Mixed Noise for Robust Retinal Disease Diagnosis
Junlin Hou, Jilan Xu, Rui Feng, Hao Chen
Label Noise Medical Image Datasets Noise Robust Learning Mixed Speech Retinal Image Datasets Retinal Disease Quality Aware Soft QMIX

March 21, 2024

SynerMix: Synergistic Mixup Solution for Enhanced Intra-Class Cohesion and Inter-Class Separability in Image Classification
Ye Xu, Ya Gao, Xiaorong Qiu, Yang Chen, Ying Ji
Image Classification Mixup Method Intra Class Class Separability Class Mixup Soft QMIX

March 5, 2024

PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning
Ke Zhang, DanDan Zhu, Qiuhan Xu, Hao Zhou, Ce Zheng
Multi Agent Reinforcement Learning Early Stage Convergence Multiple Agent Multi Agent Challenge Parameter Sharing Multi Agent Reinforcement Soft QMIX

January 22, 2024

Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classification
Chun Liu, Longwei Yang, Dongmei Dong, Zheng Li, Wei Yang, Zhigang Han, Jiayao Wang
Hyperspectral Image Spectral Information Spatial Spectral Soft QMIX Prototype Memory Shot Hyperspectral Image Classification

August 21, 2023

CoMIX: A Multi-agent Reinforcement Learning Training Architecture for Efficient Decentralized Coordination and Independent Decision-Making
Giovanni Minelli, Mirco Musolesi
Multi Agent Reinforcement Learning Multi Agent System Autonomous Decision Making Coordinated Behavior Decentralized Agent Soft QMIX Collaborative Problem Decentralized Coordination

July 3, 2023

Enhancing the Robustness of QMIX against State-adversarial Attacks
Weiran Guo, Guanjun Liu, Ziyuan Zhou, Ling Wang, Jiacun Wang
Deep Reinforcement Learning Native Robustness Multi Agent Reinforcement Learning Robust Reinforcement Learning Soft QMIX State Adversarial

November 21, 2022

TinyQMIX: Distributed Access Control for mMTC via Multi-agent Reinforcement Learning
Tien Thanh Le, Yusheng Ji, John C. S Lui
Reinforcement Learning Multi Agent Reinforcement Learning Radio Resource Management Soft QMIX Dynamic Traffic

August 7, 2022

Maximum Correntropy Value Decomposition for Multi-agent Deep Reinforcemen Learning
Kai Liu, Tianxian Zhang, Lingjiang Kong
Multi Agent Multi Agent Deep Reinforcement Learning Value Decomposition Soft QMIX Maximum Correntropy Criterion

June 14, 2022

AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data
Amin Banitalebi-Dehkordi, Pratik Gujjar, Yong Zhang
Semi Supervised Learning Auxiliary Data Soft QMIX Memorized Sample

February 9, 2022

Revisiting QMIX: Discriminative Credit Assignment by Gradient Entropy Regularization
Jian Zhao, Yue Zhang, Xunhan Hu, Weixun Wang, Wengang Zhou, Jianye Hao, Jiangcheng Zhu, Houqiang Li
Reward Signal Entropy Regularization Credit Assignment Cooperative Multi Agent System Soft QMIX

November 18, 2021

TransMix: Attend to Mix for Vision Transformers
Jie-Neng Chen, Shuyang Sun, Ju He, Philip Torr, Alan Yuille, Song Bai
Vision Transformer Supervised ImageNet Mixup Method Soft QMIX

Soft QMIX

Papers

RegMix: Data Mixture as Regression for Language Model Pre-training

VICatMix: variational Bayesian clustering and variable selection for discrete biomedical data

Soft-QMIX: Integrating Maximum Entropy For Monotonic Value Function Factorization

QMix: Quality-aware Learning with Mixed Noise for Robust Retinal Disease Diagnosis

SynerMix: Synergistic Mixup Solution for Enhanced Intra-Class Cohesion and Inter-Class Separability in Image Classification

PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning

Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classification

CoMIX: A Multi-agent Reinforcement Learning Training Architecture for Efficient Decentralized Coordination and Independent Decision-Making

Enhancing the Robustness of QMIX against State-adversarial Attacks

TinyQMIX: Distributed Access Control for mMTC via Multi-agent Reinforcement Learning

Maximum Correntropy Value Decomposition for Multi-agent Deep Reinforcemen Learning

AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data

Revisiting QMIX: Discriminative Credit Assignment by Gradient Entropy Regularization

TransMix: Attend to Mix for Vision Transformers