Deep Reinforcement Learning Based

Deep reinforcement learning (DRL) is revolutionizing control systems by enabling agents to learn optimal control policies directly from interaction with their environment, bypassing the need for explicit mathematical models. Current research emphasizes improving DRL's robustness and safety, particularly through methods like Lyapunov barrier certificates and reward martingales for verification, and intervention-assisted techniques to handle unbounded state spaces. These advancements are crucial for deploying DRL in safety-critical applications, such as autonomous vehicles, robotics, and advanced manufacturing, where reliable and verifiable control is paramount.

Papers

August 23, 2024

cc-DRL: a Convex Combined Deep Reinforcement Learning Flight Control Design for a Morphing Quadrotor
Tao Yang, Huai-Ning Wu, Jun-Wei Wang
Optimal Control Flight Control Deep Reinforcement Learning Based Free Flight Ga DRL

May 22, 2024

Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates
Udayan Mandal, Guy Amir, Haoze Wu, Ieva Daukantas, Fletcher Lee Newell, Umberto J. Ravaioli, Baoluo Meng, Michael Durling, Milan Ganai, Tobey Shim, Guy Katz, Clark Barrett
Deep Reinforcement Learning Autonomous System Deep Reinforcement Learning Based Neural Lyapunov Lyapunov Certificate

April 5, 2024

Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical Report
Jerrod Wigmore, Brooke Shrader, Eytan Modiano
Deep Reinforcement Learning Policy Gradient Technical Report Neural Network Policy Deep Reinforcement Learning Based Online Stochastic Classical Control

December 15, 2023

Robustness Verification of Deep Reinforcement Learning Based Control Systems using Reward Martingales
Dapeng Zhi, Peixin Wang, Cheng Chen, Min Zhang
Deep Reinforcement Learning Robustness Verification Deep Reinforcement Learning Based Markovian Reward

September 29, 2023

Reliability Quantification of Deep Reinforcement Learning-based Control
Hitoshi Yoshioka, Hirotada Hashimoto
Deep Reinforcement Learning DQN Agent Deep Reinforcement Learning Based Reliability Analysis Reliability Evaluation

September 27, 2023

DTC: Deep Tracking Control
Fabian Jenelten, Junzhe He, Farbod Farshidian, Marco Hutter
Trajectory Optimization Reinforcement Learning Agent Legged Locomotion Deep Reinforcement Learning Based Legged System

August 18, 2023

Reduced Order Modeling of a MOOSE-based Advanced Manufacturing Model with Operator Learning
Mahmoud Yaseen, Dewen Yushu, Peter German, Xu Wu
Operator Learning Reduced Order Deep Reinforcement Learning Based Energy Deposition Advanced Manufacturing

August 5, 2023

Surrogate Empowered Sim2Real Transfer of Deep Reinforcement Learning for ORC Superheat Control
Runze Lin, Yangyang Luo, Xialai Wu, Junghui Chen, Biao Huang, Lei Xie, Hongye Su
Deep Reinforcement Learning Formality Transfer Optimal Controller Energy Management Surrogate Assisted Version Deep Reinforcement Learning Based

April 7, 2023

A modular framework for stabilizing deep reinforcement learning control
Nathan P. Lawrence, Philip D. Loewen, Shuyuan Wang, Michael G. Forbes, R. Bhushan Gopaluni
Deep Reinforcement Learning Continuous Control Modular Framework Non Linear Operator Deep Reinforcement Learning Based Input Output

February 16, 2023

Deep Reinforcement Learning Based Tracking Control of an Autonomous Surface Vessel in Natural Waters
Wei Wang, Xiaojing Cao, Alejandro Gonzalez-Garcia, Lianhao Yin, Niklas Hagemann, Yuanyuan Qiao, Carlo Ratti, Daniela Rus
Deep Reinforcement Learning Disturbance Rejection Predictive Controller Autonomous Surface Vessel Deep Reinforcement Learning Based Autonomous Underwater

January 3, 2023

Heterogeneous Domain Adaptation and Equipment Matching: DANN-based Alignment with Cyclic Supervision (DBACS)
Natalie Gentner, Gian Antonio Susto
Transfer Learning Semiconductor Manufacturing Deep Reinforcement Learning Based Human Supervision Heterogeneous Domain Adaptation Heterogeneous Representation Product Matching

October 15, 2022

Reachable Polyhedral Marching (RPM): An Exact Analysis Tool for Deep-Learned Control Systems
Joseph A. Vincent, Mac Schwager
Reachability Analysis Reachable Set Deep Reinforcement Learning Based Invariant Set Backward Reachability Marching Cube

September 16, 2022

Toward Safe and Accelerated Deep Reinforcement Learning for Next-Generation Wireless Networks
Ahmad M. Nagib, Hatem Abou-zeid, Hossam S. Hassanein
Reinforcement Learning Deep Reinforcement Learning Radio Resource Management Deep Reinforcement Learning Based Next Generation Wireless Network

April 11, 2022

Deep Reinforcement Learning Based Semi-Autonomous Control for Robotic Surgery
Ruiqi Zhu, Dandan Zhang, Benny Lo
Robot Teleoperation Robotic Surgery Surgical Robot Deep Reinforcement Learning Based

March 28, 2022

Deep Reinforcement Learning Aided Platoon Control Relying on V2X Information
Lei Lei, Tong Liu, Kan Zheng, Lajos Hanzo
Platoon Control Deep Reinforcement Learning Based V2X Communication V2X Technology

February 2, 2022

Federated Reinforcement Learning for Collective Navigation of Robotic Swarms
Seongin Na, Tomáš Rouček, Jiří Ulrich, Jan Pikman, Tomáš Krajník, Barry Lennox, Farshad Arvin
Deep Reinforcement Learning Federated Learning Swarm Robotics Robot Swarm Federated Reinforcement Learning Deep Reinforcement Learning Based Collective Navigation

December 17, 2021

ColO-RAN: Developing Machine Learning-based xApps for Open RAN Closed-loop Control on Programmable Experimental Platforms
Michele Polese, Leonardo Bonati, Salvatore D'Oro, Stefano Basagni, Tommaso Melodia
Deep Reinforcement Learning Radio Access Network Deep Reinforcement Learning Based Open Loop Network Automation

Deep Reinforcement Learning Based

Papers

cc-DRL: a Convex Combined Deep Reinforcement Learning Flight Control Design for a Morphing Quadrotor

Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates

Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical Report

Robustness Verification of Deep Reinforcement Learning Based Control Systems using Reward Martingales

Reliability Quantification of Deep Reinforcement Learning-based Control

DTC: Deep Tracking Control

Reduced Order Modeling of a MOOSE-based Advanced Manufacturing Model with Operator Learning

Surrogate Empowered Sim2Real Transfer of Deep Reinforcement Learning for ORC Superheat Control

A modular framework for stabilizing deep reinforcement learning control

Deep Reinforcement Learning Based Tracking Control of an Autonomous Surface Vessel in Natural Waters

Heterogeneous Domain Adaptation and Equipment Matching: DANN-based Alignment with Cyclic Supervision (DBACS)

Reachable Polyhedral Marching (RPM): An Exact Analysis Tool for Deep-Learned Control Systems

Toward Safe and Accelerated Deep Reinforcement Learning for Next-Generation Wireless Networks

Deep Reinforcement Learning Based Semi-Autonomous Control for Robotic Surgery

Deep Reinforcement Learning Aided Platoon Control Relying on V2X Information

Federated Reinforcement Learning for Collective Navigation of Robotic Swarms

ColO-RAN: Developing Machine Learning-based xApps for Open RAN Closed-loop Control on Programmable Experimental Platforms