Author name cluster

Robert Babuška

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

EAAI Journal 2019 Journal Article

Reinforcement learning based compensation methods for robot manipulators

Yudha P. Pane
Subramanya P. Nageshrao
Jens Kober
Robert Babuška

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 industrial manipulators, thus rendering them ‘smart’. In this paper we introduce two reinforcement learning (RL) based compensation methods. The learned correction signal, which compensates for unmodeled aberrations, is added to the existing nominal input with an objective to enhance the control performance. The proposed learning algorithms are evaluated on a 6-DoF industrial robotic manipulator arm to follow different kinds of reference paths, such as square or a circular path, or to track a trajectory on a three dimensional surface. In an extensive experimental study we compare the performance of our learning-based methods with well-known tracking controllers, namely, proportional-derivative (PD), model predictive control (MPC), and iterative learning control (ILC). The experimental results show a considerable performance improvement thanks to our RL-based methods when compared to PD, MPC, and ILC.

Details DOI

AIJ Journal 2018 Journal Article

Decentralized Reinforcement Learning of Robot Behaviors

David L. Leottau
Javier Ruiz-del-Solar
Robert Babuška

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 multi agent DRL approaches are considered: DRL-Independent, DRL Cooperative-Adaptive (CA), and DRL-Lenient. These approaches are validated and analyzed with an extensive empirical study using four different problems: 3D Mountain Car, SCARA Real-Time Trajectory Generation, Ball-Dribbling in humanoid soccer robotics, and Ball-Pushing using differential drive robots. The experimental validation provides evidence that DRL implementations show better performances and faster learning times than their centralized counterparts, while using less computational resources. DRL-Lenient and DRL-CA algorithms achieve the best final performances for the four tested problems, outperforming their DRL-Independent counterparts. Furthermore, the benefits of the DRL-Lenient and DRL-CA are more noticeable when the problem complexity increases and the centralized scheme becomes intractable given the available computational resources and training time.

Details DOI

JMLR Journal 2018 Journal Article

Experience Selection in Deep Reinforcement Learning for Control

Tim de Bruin
Jens Kober
Karl Tuyls
Robert Babuška

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 important choices. The first is which and how many experiences to retain in the experience replay buffer. The second choice is how to sample the experiences that are to be replayed from that buffer. We propose new methods for the combined problem of experience retention and experience sampling. We refer to the combination as experience selection. We focus our investigation specifically on the control of physical systems, such as robots, where exploration is costly. To determine which experiences to keep and which to replay, we investigate different proxies for their immediate and long-term utility. These proxies include age, temporal difference error and the strength of the applied exploration noise. Since no currently available method works in all situations, we propose guidelines for using prior knowledge about the characteristics of the control problem at hand to choose the appropriate experience replay strategy. [abs] [ pdf ][ bib ] &copy JMLR 2018. ( edit, beta )

PDF Details

EAAI Journal 2018 Journal Article

Policy derivation methods for critic-only reinforcement learning in continuous spaces

Eduard Alibekov
Jiří Kubalík
Robert Babuška

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 always exhibits artifacts which damage the overall performance of the controlled system. In addition, when continuous-valued action is used, the most common approach is to discretize the action space and exhaustively search for the action that maximizes the right-hand side of the Bellman equation. Such a policy derivation procedure is computationally involved and results in steady-state error due to the lack of continuity. In this work, we propose policy derivation methods which alleviate the above problems by means of action space refinement, continuous approximation, and post-processing of the V-function by using symbolic regression. The proposed methods are tested on nonlinear control problems: 1-DOF and 2-DOF pendulum swing-up problems, and on magnetic manipulation. The results show significantly improved performance in terms of cumulative return and computational complexity.

Details DOI

EAAI Journal 2016 Journal Article

Online learning for optimistic planning

Lucian Buşoniu
Alexander Daniels
Robert Babuška

Markov decision processes are a powerful framework for nonlinear, possibly stochastic optimal control. We consider two existing optimistic planning algorithms to solve them, which originate in artificial intelligence. These algorithms have provable near-optimal performance when the actions and possible stochastic next-states are discrete, but they wastefully discard the planning data after each step. We therefore introduce a method to learn online, from this data, the upper bounds that are used to guide the planning process. Five different approximators for the upper bounds are proposed, one of which is specifically adapted to planning, and the other four coming from the standard toolbox of function approximation. Our analysis characterizes the influence of the approximation error on the performance, and reveals that for small errors, learning-based planning performs better. In detailed experimental studies, learning leads to improved performance with all five representations, and a local variant of support vector machines provides a good compromise between performance and computation.

Details DOI