382 citations · 1.2k across the 106 of their papers we have counts for
27 papers · 1 filter
Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture
Daniel Tanneberg, Elmar Rueckert, Jan Peters
A key feature of intelligent behavior is the ability to learn abstract strategies that transfer to unfamiliar problems. Therefore, we present a novel architecture, based on memory-…
Generalized Mean Estimation in Monte-Carlo Tree Search
Tuan Dam, Pascal Klink, Carlo D'Eramo +2
We consider Monte-Carlo Tree Search (MCTS) applied to Markov Decision Processes (MDPs) and Partially Observable MDPs (POMDPs), and the well-known Upper Confidence bound for Trees (…
HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints
Michael Lutter, Boris Belousov, Kim Listmann +2
Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learni…
Receding Horizon Curiosity
Matthias Schultheis, Boris Belousov, Hany Abdulsamad +1
Sample-efficient exploration is crucial not only for discovering rewarding experiences but also for adapting to environment changes in a task-agnostic fashion. A principled treatme…
Self-Paced Contextual Reinforcement Learning
Pascal Klink, Hany Abdulsamad, Boris Belousov +1
Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a p…
Stochastic Optimal Control as Approximate Input Inference
Joe Watson, Hany Abdulsamad, Jan Peters
Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning. Given the intractability of the global control problem, state-of-the…
Building a Library of Tactile Skills Based on FingerVision
Boris Belousov, Alymbek Sadybakasov, Bastian Wibranek +3
Camera-based tactile sensors are emerging as a promising inexpensive solution for tactile-enhanced manipulation tasks. A recently introduced FingerVision sensor was shown capable o…
Reliable Real Time Ball Tracking for Robot Table Tennis
Sebastian Gomez-Gonzalez, Yassine Nemmour, Bernhard Schölkopf +1
Robot table tennis systems require a vision system that can track the ball position with low latency and high sampling rate. Altering the ball to simplify the tracking using for in…
Model-based Lookahead Reinforcement Learning
Zhang-Wei Hong, Joni Pajarinen, Jan Peters
Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficie…
Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems
Michael Lutter, Kim Listmann, Jan Peters
Applying Deep Learning to control has a lot of potential for enabling the intelligent design of robot control laws. Unfortunately common deep learning approaches to control, such a…
Experience Reuse with Probabilistic Movement Primitives
Svenja Stark, Jan Peters, Elmar Rueckert
Acquiring new robot motor skills is cumbersome, as learning a skill from scratch and without prior knowledge requires the exploration of a large space of motor configurations. Acco…
Chance-Constrained Trajectory Optimization for Non-linear Systems with Unknown Stochastic Dynamics
Onur Celik, Hany Abdulsamad, Jan Peters
Iterative trajectory optimization techniques for non-linear dynamical systems are among the most powerful and sample-efficient methods of model-based reinforcement learning and app…
Neural Signatures of Motor Skill in the Resting Brain
Ozan Özdenizci, Timm Meyer, Felix Wichmann +4
Stroke-induced disturbances of large-scale cortical networks are known to be associated with the extent of motor deficits. We argue that identifying brain networks representative o…
Entropic Regularization of Markov Decision Processes
Boris Belousov, Jan Peters
An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the rewar…
Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
Michael Lutter, Christian Ritter, Jan Peters
Deep learning has achieved astonishing results on many tasks with large amounts of data and generalization within the proximity of training data. For many important real-world appl…
Generalized Multiple Correlation Coefficient as a Similarity Measurements between Trajectories
Julen Urain, Jan Peters
Similarity distance measure between two trajectories is an essential tool to understand patterns in motion, for example, in Human-Robot Interaction or Imitation Learning. The probl…
Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction
Susanne Trick, Dorothea Koert, Jan Peters +1
Assistive robots can potentially improve the quality of life and personal independence of elderly people by supporting everyday life activities. To guarantee a safe and intuitive i…
Assessing Transferability from Simulation to Reality for Reinforcement Learning
Fabio Muratore, Michael Gienger, Jan Peters
Learning robot control policies from physics simulations is of great interest to the robotics community as it may render the learning process faster, cheaper, and safer by alleviat…
Local Online Motor Babbling: Learning Motor Abundance of A Musculoskeletal Robot Arm
Zinan Liu, Arne Hitzmann, Shuhei Ikemoto +3
Motor babbling and goal babbling has been used for sensorimotor learning of highly redundant systems in soft robotics. Recent works in goal babbling has demonstrated successful lea…
Entropic Risk Measure in Policy Search
David Nass, Boris Belousov, Jan Peters
With the increasing pace of automation, modern robotic systems need to act in stochastic, non-stationary, partially observable environments. A range of algorithms for finding param…
Learning walk and trot from the same objective using different types of exploration
Zinan Liu, Kai Ploeger, Svenja Stark +2
In quadruped gait learning, policy search methods that scale high dimensional continuous action spaces are commonly used. In most approaches, it is necessary to introduce prior kno…
Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots
Dieter Büchler, Roberto Calandra, Jan Peters
High-speed and high-acceleration movements are inherently hard to control. Applying learning to the control of such motions on anthropomorphic robot arms can improve the accuracy o…
Information Gathering in Decentralized POMDPs by Policy Graph Improvement
Mikko Lauri, Joni Pajarinen, Jan Peters
Decentralized policies for information gathering are required when multiple autonomous agents are deployed to collect data about a phenomenon of interest without the ability to com…
Was ist eine Professur fuer Kuenstliche Intelligenz?
Kristian Kersting, Jan Peters, Constantin Rothkopf
The Federal Government of Germany aims to boost the research in the field of Artificial Intelligence (AI). For instance, 100 new professorships are said to be established. However,…