382 citations · 1.2k across the 106 of their papers we have counts for
10 papers · 1 filter
TD-Regularized Actor-Critic Methods
Simone Parisi, Voot Tangkaratt, Jan Peters +1
Actor-critic methods can achieve incredible performance on difficult reinforcement learning problems, but they are also prone to instability. This is partly due to the interaction…
An Algorithmic Perspective on Imitation Learning
Takayuki Osa, Joni Pajarinen, Gerhard Neumann +3
As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingl…
Learning to serve: an experimental study for a new learning from demonstrations framework
Okan Koc, Jan Peters
Learning from demonstrations is an easy and intuitive way to show examples of successful behavior to a robot. However, the fact that humans optimize or take advantage of their body…
Adaptation and Robust Learning of Probabilistic Movement Primitives
Sebastian Gomez-Gonzalez, Gerhard Neumann, Bernhard Schölkopf +1
Probabilistic representations of movement primitives open important new possibilities for machine learning in robotics. These representations are able to capture the variability of…
Optimizing Execution of Dynamic Goal-Directed Robot Movements with Learning Control
Okan Koc, Guilherme Maeda, Jan Peters
Highly dynamic tasks that require large accelerations and precise tracking usually rely on accurate models and/or high gain feedback. While kinematic optimization allows for effici…
In-Hand Object Stabilization by Independent Finger Control
Filipe Veiga, Benoni B. Edin, Jan Peters
Grip control during robotic in-hand manipulation is usually modeled as part of a monolithic task, relying on complex controllers specialized for specific situations. Such approache…
Probabilistic Trajectory Segmentation by Means of Hierarchical Dirichlet Process Switching Linear Dynamical Systems
Maximilian Sieb, Matthias Schultheis, Sebastian Szelag +2
Using movement primitive libraries is an effective means to enable robots to solve more complex tasks. In order to build these movement libraries, current algorithms require a prio…
Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling
Adrian Šošić, Elmar Rueckert, Jan Peters +2
Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behav…
Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks
Daniel Tanneberg, Jan Peters, Elmar Rueckert
Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-le…
f-Divergence constrained policy improvement
Boris Belousov, Jan Peters
To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the informatio…