de Bruin, Tim and Kober, Jens and Tuyls, Karl and Babuska, Robert, Fine-tuning Deep RL with Gradient-Free Optimization , 21th IFAC World Congress, 53 (2), 8049-8056, 2020. [DOI] [PDF] [Code]
Deep Learning for Robust Robot Control (DL-foRCe)
Abstract:
While robots can flawlessly execute a set of commands to achieve a task, these commands are mostly encoded by hand. There is a need for effective learning methods that can deal with the uncertainty in the robot's environment, in particular when only broad goals are specified, and the learning algorithm has to learn motor commands to achieve these goals. This typically involves reinforcement learning (RL). However, current RL for robotics tasks relies on ad hoc function approximators and is typically not robust to changes in the task, environment, or robot uncertainty (compliant robot actuators, or wear and tear). The aim of this project is to integrate two emerging notions in order to make reinforcement learning for robot control more robust and efficient: dynamic feedback control policies for robust control combined with deep neural networks to learn low-dimensional parameterizations of such control policies. This approach promises a generic and robust approach to reinforcement learning for robotic control.
Project Type: NWO Natural Artificial Intelligence; 2015-2019
Members: ir. Tim de Bruin , Dr.-Ing. Jens Kober , Prof Dr Sander Bohté , Prof Karl Tuyls , prof.dr. Robert Babuška
Publications
Buc soniu, Lucian and de Bruin, Tim and Tolic, Domagoj and Kober, Jens and Palunko, Ivana, Reinforcement Learning for Control: Performance, Stability, and Deep Approximators , Annual Reviews in Control, 46, 8--28, 2018. [DOI] [PDF]
de Bruin, Tim and Kober, Jens and Tuyls, Karl and Babuska, Robert, Integrating State Representation Learning into Deep Reinforcement Learning , IEEE Robotics and Automation Letters, 3 (3), 1394--1401, 2018. [DOI] [PDF]
de Bruin, Tim and Kober, Jens and Tuyls, Karl and Babuska, Robert, Experience Selection in Deep Reinforcement Learning for Control , Journal of Machine Learning Research, 19 (9), 1--56, 2018. [PDF] [Video] [Code] [Website]
de Bruin, Tim and Kober, Jens and Tuyls, Karl and Babuska, Robert, Off Policy Experience Retention for Deep Actor Critic Learning , Deep Reinforcement Learning Workshop, Advances in Neural Information Processing Systems (NIPS), 2016. [PDF]
de Bruin, Tim and Kober, Jens and Tuyls, Karl and Babuska, Robert, Improved Deep Reinforcement Learning for Robotics Through Distribution-based Experience Retention , IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 3947--3952, 2016. [DOI] [PDF] [Video]
de Bruin, Tim and Kober, Jens and Tuyls, Karl and Babuska, Robert, The Importance of Experience Replay Database Composition in Deep Reinforcement Learning , Deep Reinforcement Learning Workshop, Advances in Neural Information Processing Systems (NIPS), 2015. [PDF] [Video]