- document
-
van der Heijden, D.S. (author), Ferranti, L. (author), Kober, J. (author), Babuska, R. (author)This paper presents DeepKoCo, a novel modelbased agent that learns a latent Koopman representation from images. This representation allows DeepKoCo to plan efficiently using linear control methods, such as linear model predictive control. Compared to traditional agents, DeepKoCo learns taskrelevant dynamics, thanks to the use of a tailored lossy...conference paper 2021
- document
-
Kubalík, Jiří (author), Derner, Erik (author), Babuska, R. (author)Virtually all dynamic system control methods benefit from the availability of an accurate mathematical model of the system. This includes also methods like reinforcement learning, which can be vastly sped up and made safer by using a dynamic system model. However, obtaining a sufficient amount of informative data for constructing dynamic...journal article 2021
- document
-
Kubalik, Jiri (author), Derner, Erik (author), Zegklitz, Jan (author), Babuska, R. (author)Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as neural networks or basis...journal article 2021
- document
-
Derner, Erik (author), Kubalik, Jiri (author), Babuska, R. (author)Continual model learning for nonlinear dynamic systems, such as autonomous robots, presents several challenges. First, it tends to be computationally expensive as the amount of data collected by the robot quickly grows in time. Second, the model accuracy is impaired when data from repetitive motions prevail in the training set and outweigh...journal article 2021
- document
-
de Bruin, T.D. (author), Kober, J. (author), Tuyls, Karl (author), Babuska, R. (author)Deep reinforcement learning makes it possible to train control policies that map high-dimensional observations to actions. These methods typically use gradient-based optimization techniques to enable relatively efficient learning, but are notoriously sensitive to hyperparameter choices and do not have good convergence properties. Gradient...journal article 2020
- document
-
Verdier, C.F. (author), Babuska, R. (author), Shyrokau, B. (author), Mazo, M. (author)Control systems designed via learning methods, aiming at quasi-optimal solutions, typically lack stability and performance guarantees. We propose a method to construct a near-optimal control law by means of model-based reinforcement learning and subsequently verifying the reachability and safety of the closed-loop control system through an...journal article 2019
- document
-
Pane, Yudha P. (author), Nageshrao, Subramanya P. (author), Kober, J. (author), Babuska, R. (author)Smart robotics will be a core feature while migrating from Industry 3.0 (i.e., mass manufacturing) to Industry 4.0 (i.e., customized or social manufacturing). A key characteristic of a smart system is its ability to learn. For smart manufacturing, this means incorporating learning capabilities into the current fixed, repetitive, task-oriented...journal article 2019
- document
-
Alibekov, Eduard (author), Kubalík, Jiří (author), Babuska, R. (author)Approximate Reinforcement Learning (RL) is a method to solve sequential decisionmaking and dynamic control problems in an optimal way. This paper addresses RL for continuous state spaces which derive the control policy by using an approximate value function (V-function). The standard approach to derive a policy through the V-function is...journal article 2019
- document
-
van der Weijde, J.O. (author), Vallery, H. (author), Babuska, R. (author)The twisted and coiled polymer muscle (TCPM) has two major benefits: low weight and low cost. Therefore, this new type of actuator is increasingly used in robotic applications where these benefits are relevant. Closed-loop control of these muscles, however, requires additional sensors that add weight and cost, negating the muscles' intrinsic...journal article 2019
- document
-
Leottau, David L. (author), Ruiz-del-Solar, Javier (author), Babuska, R. (author)A multi-agent methodology is proposed for Decentralized Reinforcement Learning (DRL) of individual behaviors in problems where multi-dimensional action spaces are involved. When using this methodology, sub-tasks are learned in parallel by individual agents working toward a common goal. In addition to proposing this methodology, three specific...journal article 2018
- document
-
Alibekov, Eduard (author), Kubalik, Jiri (author), Babuska, R. (author)This paper addresses the problem of deriving a policy from the value function in the context of critic-only reinforcement learning (RL) in continuous state and action spaces. With continuous-valued states, RL algorithms have to rely on a numerical approximator to represent the value function. Numerical approximation due to its nature virtually...journal article 2018
- document
-
de Bruin, T.D. (author), Kober, J. (author), Tuyls, K.P. (author), Babuska, R. (author)Experience replay is a technique that allows off-policy reinforcement-learning methods to reuse past experiences. The stability and speed of convergence of reinforcement learning, as well as the eventual performance of the learned policy, are strongly dependent on the experiences being replayed. Which experiences are replayed depends on two...journal article 2018
- document
-
Koryakovskiy, I. (author), Kudruss, M. (author), Babuska, R. (author), Caarls, W. (author), Kirches, Christian (author), Mombaur, Katja (author), Schlöder, Johannes P. (author), Vallery, H. (author)Model-free reinforcement learning and nonlinear model predictive control are two different approaches for controlling a dynamic system in an optimal way according to a prescribed cost function. Reinforcement learning acquires a control policy through exploratory interaction with the system, while nonlinear model predictive control exploits an...journal article 2017
- document
-
Koryakovskiy, I. (author), Vallery, H. (author), Babuska, R. (author), Caarls, W. (author)Reinforcement learning techniques enable robots to deal with their own dynamics and with unknown environments without using explicit models or preprogrammed behaviors. However, reinforcement learning relies on intrinsically risky exploration, which is often damaging for physical systems. In the case of the bipedal walking robot Leo, which is...journal article 2017
- document
-
Beyhan, Selami (author), Eghbal Sarabi, F. (author), Lendek, Zsofia (author), Babuska, R. (author)In this paper, a novel adaptive Takagi-Sugeno (TS) fuzzy observer-based controller is proposed. The closed-loop stability and the boundedness of all the signals are proven by Lyapunov stability analysis. The proposed controller is applied to a flexible-transmission experimental setup. The performance for constant payload in the presence of...journal article 2017
- document
-
Kubalík, Jiří (author), Alibekov, Eduard (author), Babuska, R. (author)Model-based reinforcement learning (RL) algorithms can be used to derive optimal control laws for nonlinear dynamic systems. With continuous-valued state and input variables, RL algorithms have to rely on function approximators to represent the value function and policy mappings. This paper addresses the problem of finding a smooth policy...journal article 2017
- document
-
Berry, Andrew (author), Lemus Perez, D.S. (author), Babuska, R. (author), Vallery, H. (author)Gyroscopic actuation is appealing for wearable applications due to its ability to impart free moments on a body without exoskeletal structures on the joints.We recently proposed an unobtrusive balancing aid consisting of multiple parallelmounted control moment gyroscopes (CMGs) contained within a backpack-like orthopedic corset. Using...journal article 2016
- document
-
de Bruin, T.D. (author), Kober, J. (author), Tuyls, K.P. (author), Babuska, R. (author)Recent years have seen a growing interest in the use of deep neural networks as function approximators in reinforcement learning. In this paper, an experience replay method is proposed that ensures that the distribution of the experiences used for training is between that of the policy and a uniform distribution. Through experiments on a...conference paper 2016
- document
-
Busoniu, L. (author), Babuska, R. (author), De Schutter, B. (author)Multiagent systems are rapidly finding applications in a variety of domains, including robotics, distributed control, telecommunications, and economics. The complexity ofmany tasks arising in these domains makes them difficult to solve with preprogrammed agent behaviors. The agents must, instead, discover a solution on their own, using learning....journal article 2008
- document
- Babuska, R. (author), Sousa, J. (author), Verbruggen, H.B. (author) conference paper 1995