Multi Objective Deep Reinforcement Learning

Multi-objective deep reinforcement learning (MODRL) addresses the challenge of optimizing multiple, often conflicting, objectives simultaneously within complex systems using deep neural networks. Current research focuses on applying MODRL to diverse real-world problems, including traffic control, resource allocation in e-commerce, and infrastructure maintenance, employing algorithms like Deep Q-Networks (DQN) variants, Proximal Policy Optimization (PPO), and evolutionary multi-objective approaches. These advancements enable the development of more robust and adaptable systems by directly optimizing for multiple performance metrics, leading to improved efficiency, safety, and fairness across various applications.

Papers

August 2, 2024

Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems
Juan C. Rosero, Ivana Dusparic, Nicolás Cardozo
Reinforcement Learning Q Learning Autonomous System Multi Objective Optimization Multi Objective Reinforcement Learning Optimization Process DQN Agent Multi Objective Deep Reinforcement Learning

August 1, 2024

Adaptive traffic signal safety and efficiency improvement by multi objective deep reinforcement learning approach
Shahin Mirbakhsh, Mahdi Azizi
High Efficiency Traffic Signal Control Adaptive Traffic Signal Control Multi Objective Deep Reinforcement Learning

July 22, 2024

MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search
Peng Cheng, Huimu Wang, Jinyuan Zhao, Yihao Wang, Enqiang Xu, Yu Zhao, Zhuojian Xiao, Songlin Wang, Guoyu Tang, Lin Liu, Sulong Xu
Reinforcement Learning E Commerce Search Multi Objective Deep Reinforcement Learning Traffic Allocation

June 10, 2024

Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization
Jesse van Remmerden, Maurice Kenter, Diederik M. Roijers, Charalampos Andriotis, Yingqian Zhang, Zaharah Bukhsh
Multi Objective Reinforcement Learning Multi Objective Deep Reinforcement Learning

April 11, 2024

Collaborative Ground-Space Communications via Evolutionary Multi-objective Deep Reinforcement Learning
Jiahui Li, Geng Sun, Qingqing Wu, Dusit Niyato, Jiawen Kang, Abbas Jamalipour, Victor C. M. Leung
Uplink Control Multi Objective Deep Reinforcement Learning Joint Beamforming

April 9, 2024

Learning Efficient and Fair Policies for Uncertainty-Aware Collaborative Human-Robot Order Picking
Igor G. Smit, Zaharah Bukhsh, Mykola Pechenizkiy, Kostas Alogariastos, Kasper Hendriks, Yingqian Zhang
Efficient Learning Human Robot Autonomous Mobile Robot Multi Objective Deep Reinforcement Learning Allocation Policy

March 20, 2024

M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling
Xudong Sun, Nutan Chen, Alexej Gossmann, Yu Xing, Carla Feistner, Emilio Dorigatt, Felix Drost, Daniele Scarcella, Lisa Beer, Carsten Marr
Multi Objective Optimization Multi Objective Loss Landscape Multi Objective Deep Reinforcement Learning Multiplier Design

December 4, 2023

AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design
Romain Lacombe, Lucas Hendren, Khalid El-Awady
Multi Objective Deep Reinforcement Learning Inverse Molecular Design Adsorption Energy Adsorbate Placement

July 5, 2023

Multi-objective Deep Reinforcement Learning for Mobile Edge Computing
Ning Yang, Junrui Wen, Meng Zhang, Ming Tang
Proximal Policy Optimization Mobile Edge Computing Multi Objective Deep Reinforcement Learning Next Generation Wireless Network

June 19, 2023

Forest Parameter Prediction by Multiobjective Deep Learning of Regression Models Trained with Pseudo-Target Imputation
Sara Björk, Stian N. Anfinsen, Michael Kampffmeyer, Erik Næsset, Terje Gobakken, Lennart Noordermeer
Regression Model Knowledge Enhanced Conditional Imputation Forest Monitoring Multi Objective Deep Reinforcement Learning Target Prediction Random Forest Prediction Aboveground Biomass Pseudo Target

June 13, 2023

Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care
Ali Shirali, Alexander Schubert, Ahmed Alaa
Reinforcement Learning Constructive Approach Reward Function Edge Pruning Deep Q Learning Conservative Q Learning Intensive Care Multi Objective Deep Reinforcement Learning

March 15, 2023

Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning
Takuya Kanazawa, Chetan Gupta
Policy Gradient Multi Objective Reinforcement Learning Sequential Decision Making Pareto Set Multi Objective Deep Reinforcement Learning Pareto Optimal Policy

October 3, 2022

Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications
Mingyu Cai, Makai Mann, Zachary Serlin, Kevin Leahy, Cristian-Ioan Vasile
LeArning Abstract Deep Reinforcement Learning Temporal Logic Navigation Task Continuous Control Control Synthesis Multi Objective Deep Reinforcement Learning

October 1, 2022

Multi-objective Deep Data Generation with Correlated Property Control
Shiyu Wang, Xiaojie Guo, Xuanyang Lin, Bo Pan, Yuanqi Du, Yinkai Wang, Yanfang Ye, Ashley Ann Petersen, Austin Leitgeb, Saleh AlKhalifa, Kevin Minbiole, William Wuest, Amarda Shehu, Liang Zhao
Generative Model Latent Vector Multi Objective Deep Reinforcement Learning

April 11, 2022

gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach
Johannes Dornheim
Deep Reinforcement Learning Multi Objective Reinforcement Learning Multi Objective Deep Reinforcement Learning Real World Decision

February 22, 2022

Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach
Yizhou Yang, Xin Liu
Multi Objective Reinforcement Learning Penetration Testing Multi Objective Deep Reinforcement Learning

Multi Objective Deep Reinforcement Learning

Papers

Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems

Adaptive traffic signal safety and efficiency improvement by multi objective deep reinforcement learning approach

MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search

Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization

Collaborative Ground-Space Communications via Evolutionary Multi-objective Deep Reinforcement Learning

Learning Efficient and Fair Policies for Uncertainty-Aware Collaborative Human-Robot Order Picking

M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling

AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design

Multi-objective Deep Reinforcement Learning for Mobile Edge Computing

Forest Parameter Prediction by Multiobjective Deep Learning of Regression Models Trained with Pseudo-Target Imputation

Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care

Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning

Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications

Multi-objective Deep Data Generation with Correlated Property Control

gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach

Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach