Continuous Control

Continuous control focuses on designing algorithms that enable robots and other systems to smoothly and precisely execute actions in continuous state and action spaces, aiming for optimal performance and stability. Current research emphasizes improving sample efficiency through techniques like coarse-to-fine reinforcement learning, model-based methods, and efficient exploration strategies, often employing neural networks (e.g., actor-critic architectures, transformers) and advanced optimization techniques. These advancements are crucial for deploying robust and reliable continuous control in real-world applications, such as robotics, autonomous driving, and process control, where precise and adaptable control is essential.

Papers

July 5, 2023

Dynamic Feature-based Deep Reinforcement Learning for Flow Control of Circular Cylinder with Sparse Surface Pressure Sensing
Qiulei Wang, Lei Yan, Gang Hu, Wenli Chen, Jean Rabault, Bernd R. Noack
Continuous Control Flow Control Minutia Cylinder Code Wake Model Active Flow Control

June 6, 2023

RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control
Jonas Eschmann, Dario Albani, Giuseppe Loianno
Reinforcement Learning Deep Reinforcement Learning Reinforcement Learning Algorithm Continuous Control Tiny Machine Learning Reinforcement Learning Library

May 29, 2023

Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse
Jiafei Lyu, Le Wan, Zongqing Lu, Xiu Li
Q Learning Policy Reinforcement Learning Online Reinforcement Learning Continuous Control Independent Sampling

May 2, 2023

Validation of massively-parallel adaptive testing using dynamic control matching
Schaun Wheeler
Test Time Adaptation External Validation Continuous Control Marketing Optimization

April 20, 2023

Aiding reinforcement learning for set point control
Ruoqi Zhang, Per Mattsson, Torbjörn Wigren
Reinforcement Learning Continuous Control

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

March 30, 2023

Switching Pushing Skill Combined MPC and Deep Reinforcement Learning for Planar Non-prehensile Manipulation
Bo Zhang, Cong Huang, Haixu Zhang, Xiaoshan Bai
Deep Reinforcement Learning Predictive Control Model Predictive Control Continuous Control UNO Push Non Prehensile Planar Manipulation

March 29, 2023

Learning Flow Functions from Data with Applications to Nonlinear Oscillators
Miguel Aguiar, Amritam Das, Karl H. Johansson
Financial Application Raw Data Recurrent Neural Network Discrete Time Continuous Control Flow Based Flow Based Model Nonlinear Oscillator

March 27, 2023

Closed-Loop Koopman Operator Approximation
Steven Dahdah, James Richard Forbes
Koopman Operator Continuous Control Open Loop

March 24, 2023

Multi-Task Reinforcement Learning in Continuous Control with Successor Feature-Based Concurrent Composition
Yu Tang Liu, Aamir Ahmad
Deep Reinforcement Learning Multi Task Continuous Control Multi Task Reinforcement Learning Multi Task Agent Novel Predecessor and Successor Compositional Capability

March 17, 2023

Energy-Efficient Control of Cable Robots Exploiting Natural Dynamics and Task Knowledge
Boris Deroo, Erwin Aertbeliën, Wilm Decré, Herman Bruyninckx
Continuous Control Task Specific Knowledge Pick and Place Cable Driven Hybrid Control Energy Efficient Control

March 14, 2023

RE-MOVE: An Adaptive Policy Design for Robotic Navigation Tasks in Dynamic Environments via Language-Based Feedback
Souradip Chakraborty, Kasun Weerakoon, Prithvi Poddar, Mohamed Elnoor, Priya Narayanan, Carl Busart, Pratap Tokekar, Amrit Singh Bedi, Dinesh Manocha
Dynamic Environment Navigation Task Continuous Control Adaptive Policy Language Feedback MOVE Brilliance

March 4, 2023

CFlowNets: Continuous Control with Generative Flow Networks
Yinchuan Li, Shuang Luo, Haozhi Wang, Jianye Hao
Reinforcement Learning Continuous Control Generative Flow Network Task Driven Exploration

February 27, 2023

Continuous descriptor-based control for deep audio synthesis
Ninon Devis, Nils Demerlé, Sarah Nabi, David Genova, Philippe Esling
Generative Model Real Time Music Generation Continuous Control Generative Audio Neural Audio Synthesis

February 14, 2023

Learning a model is paramount for sample efficiency in reinforcement learning control of PDEs
Stefan Werner, Sebastian Peitz
Reinforcement Learning LeArning Abstract Full Model Dynamical System Continuous Control Sample Efficiency Dynamical Model Data Driven Surrogate

December 25, 2022

Temporally Layered Architecture for Adaptive, Distributed and Continuous Control
Devdhar Patel, Joshua Russell, Francesca Walsh, Tauhidur Rahman, Terrence Sejnowski, Hava Siegelmann
Adaptive Importance Continuous Control Continuous Control Task Temporal Abstraction

December 2, 2022

STL-Based Synthesis of Feedback Controllers Using Reinforcement Learning
Nikhil Kumar Singh, Indranil Saha
Reinforcement Learning Deep Reinforcement Learning Critical Synthesis Continuous Control Signal Temporal Logic Reward Structure

November 7, 2022

On the importance of data collection for training general goal-reaching policies
Alexis Jacq, Manu Orsini, Gabriel Dulac-Arnold, Olivier Pietquin, Matthieu Geist, Olivier Bachem
Reinforcement Learning Importance Aware Data Collection Continuous Control Language Task Policy Design Unsupervised Exploration

October 27, 2022

Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection
Catherine R. Glossop, Jacopo Panerati, Amrit Krishnan, Zhaocong Yuan, Angela P. Schoellig
Reinforcement Learning Native Robustness Action Space Continuous Control Robust Reinforcement Learning Disturbance Injection

October 22, 2022

Solving Continuous Control via Q-learning
Tim Seyde, Peter Werner, Wilko Schwarting, Igor Gilitschenski, Martin Riedmiller, Daniela Rus, Markus Wulfmeier
Q Learning Actor Critic Deep Q Learning Continuous Control

Continuous Control

Papers

Dynamic Feature-based Deep Reinforcement Learning for Flow Control of Circular Cylinder with Sparse Surface Pressure Sensing

RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control

Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse

Validation of massively-parallel adaptive testing using dynamic control matching

Aiding reinforcement learning for set point control

A modular framework for stabilizing deep reinforcement learning control

Switching Pushing Skill Combined MPC and Deep Reinforcement Learning for Planar Non-prehensile Manipulation

Learning Flow Functions from Data with Applications to Nonlinear Oscillators

Closed-Loop Koopman Operator Approximation

Multi-Task Reinforcement Learning in Continuous Control with Successor Feature-Based Concurrent Composition

Energy-Efficient Control of Cable Robots Exploiting Natural Dynamics and Task Knowledge

RE-MOVE: An Adaptive Policy Design for Robotic Navigation Tasks in Dynamic Environments via Language-Based Feedback

CFlowNets: Continuous Control with Generative Flow Networks

Continuous descriptor-based control for deep audio synthesis

Learning a model is paramount for sample efficiency in reinforcement learning control of PDEs

Temporally Layered Architecture for Adaptive, Distributed and Continuous Control

STL-Based Synthesis of Feedback Controllers Using Reinforcement Learning

On the importance of data collection for training general goal-reaching policies

Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection

Solving Continuous Control via Q-learning