Machine Learning-based Control

A curated list of resources dedicated to theory and applications of machine learning to Control Theory and Engineering (Emphasis on Large Scale Control and Deep Learning)

• Maintainers
  • Olalekan Ogunmolu

Table of Contents

• Papers and Codes

  • Continuous Action Reinforcement Learning for Control-Affine Systems with Unknown Dynamics
  • Preference-balancing Motion Planning under Stochastic Disturbances
  • Adaptive Human-Inspired Compliant Contact Primitives to Perform Surface-Surface Contact under Uncertainty
  • Learning Potential Functions from Human Demonstrations with Encapsulated Dynamic and Compliant Behaviors
  • Learning Stable Non-Linear Dynamical Systems with Gaussian Mixture Models
  • Learning Control Lyapunov Function to Ensure Stability of Dynamical System-based Robot Reaching Motions
  • A Dynamical System Approach to Realtime Obstacle Avoidance
  • FeUdal Networks for Hierarchical Reinforcement Learning
  • Optnet: Differentiable Optimization as a Layer in Neural Networks
  • qpth: A fast and differentiable Quadratic Programming solver for PyTorch
  • How hard is it to cross the room? - Training (Recurrent) Neural Networks to steer a UAV
  • Neural Episodic Control
  • Inferring and Executing Programs for Visual Reasoning
  • Dynamical Systems approach to Learn Robot Motions
  • Learning representations by backpropagating errors

• Foundational Papers on Modern Machine Learning

  • Course on Information Theory, Pattern Recognition, and Neural Networks
  • Approximation by Superpositions of a Sigmoidal Function. Approximation Theory and Its Applications
  • On the approximate realization of continuous mappings by neural networks..
  • Parallel networks that learn to pronounce English text. Complex Systems

Papers and Codes

• Dynamical Systems approach to Learn Robot Motions
  • Ecole Polytechnique Federale de Lausanne, LASA Laboratory

• Continuous Action Reinforcement Learning for Control-Affine Systems with Unknown Dynamics
  • Author: Aleksandra Faust
  • Institution Affiliation: University of New Mexico

• Preference-balancing Motion Planning under Stochastic Disturbances
  • Author: Aleksandra Faust
  • Institution Affiliation: University of New Mexico

• Adaptive Human-Inspired Compliant Contact Primitives to Perform Surface-Surface Contact under Uncertainty
  • Authors: S.M. Khansari-Zadeh, E. Klingbeil, and O. Khatib (2016)
  • Institution: Stanford
  • Journal: The International Journal of Robotics Research

• Learning Potential Functions from Human Demonstrations with Encapsulated Dynamic and Compliant Behaviors
• Authors: S.M. Khansari-Zadeh and O. Khatib (2015)
• Institution: Stanford
• Journal: Autonomous Robots.

• Learning Stable Non-Linear Dynamical Systems with Gaussian Mixture Models
  • Institution: Stanford
  • Authors: S.M. Khansari-Zadeh and A. Billard (2011), L,
  • Journal: IEEE Transaction on Robotics, vol. 27, num 5, p. 943-957.

• Learning Control Lyapunov Function to Ensure Stability of Dynamical System-based Robot Reaching Motions
  • Institution: Stanford
  • Authors: S.M. Khansari-Zadeh and A. Billard (2014),
  • Journal: Robotics and Autonomous Systems, vol. 62, num 6, p. 752-765.

• A Dynamical System Approach to Realtime Obstacle Avoidance
  • Authors: S.M. Khansari-Zadeh and A. Billard (2012),
  • Journal: Autonomous Robots, vol. 32, num 4, p. 433-454.

• ADAPT: Zero-Shot Adaptive Policy Transfer for Stochastic Dynamical Systems
  • Authors: James Harrison, Animesh Garg, Boris Ivanovic, Yuke Zhu, Silvio Savarese, Li Fei-Fei, Marco Pavone
  • Institute: Stanford

• Emergence of Locomotion Behaviours in Rich Environments
  • Authors: Nicolas Heess, Dhruva TB, Srinivasan Sriram, Jay Lemmon, Josh Merel, Greg Wayne, Yuval Tassa, Tom Erez, Ziyu Wang, Ali Eslami, Martin Riedmiller, David Silver
  • Institution: DeepMind

• Input Convex Neural Networks
  • Authors: Brandon Amos, J. Zico Kolter
  • Institution: CMU

• FeUdal Networks for Hierarchical Reinforcement Learning
  • Authors: Alexander Sasha Vezhnevets, Simon Osindero, Tom Schaul, Nicolas Heess, Max Jaderberg, David Silver, Koray Kavukcuoglu
  • Institution: Google

• Optnet: Differentiable Optimization as a Layer in Neural Networks

  • Code
  • Authors: Brandon Amos and J. Zico Kolter. (3/2017).
  • Institution Affiliation: CMU

• Primal-Dual Interior Methods

  • Vanderberghe, UCLA

• qpth: A fast and differentiable Quadratic Programming solver for PyTorch
  • Code
  • Authors: Brandon Amos and J. Zico Kolter. (3/2017).
  • Institution Affiliation: CMU

• How hard is it to cross the room? - Training (Recurrent) Neural Networks to steer a UAV
  • Authors: Klaas Kelchtermans and Tinne Tuytelaars. (3/2017).
  • Institution Affiliation: KU Leuven

• Neural Episodic Control
  • Authors: Alexander Pritzel, Benigno Uria, Sriram Srinivasan, Adrià Puigdomènech, Oriol Vinyals, Demis Hassabis, Daan Wierstra, Charles Blundell
  • Google/DeepMind

• Inferring and Executing Programs for Visual Reasoning
  • Authors: Justin C. Johnson, Bharath Hariharan, Laurens van der Maaten, Judy Hoffman, Li Fei-Fei, C. Lawrence Zitnick, Ross Girshick

Foundational Papers on Modern Machine Learning

• Course on Information Theory, Pattern Recognition, and Neural Networks
  • Author: Sir David MacKay
  • Institution Affiliation: University of Cambridge

• Approximation by Superpositions of a Sigmoidal Function. Approximation Theory and Its Applications
  • Author: Cybenko, G. (1993).
  • Institution Affiliation: University of Illinois

• On the approximate realization of continuous mappings by neural networks.
  • Author: Ken-Ichi Funahashi, 5/1988
  • Institution Affiliation: CMU

• Parallel networks that learn to pronounce English text. Complex Systems
  • Sejnowski, T. J., & Rosenberg, C. R. (1987).
  • Institution Affiliation: Johns Hopkins University/Princeton University

• Learning representations by backpropagating errors.
  • Rumelhart, D. E., & Hinton, G. E. (1986).
  • Institution Affiliation: UToronto