• Publications
  • Influence
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
TLDR
Embed to Control is introduced, a method for model learning and control of non-linear dynamical systems from raw pixel images that is derived directly from an optimal control formulation in latent space and exhibits strong performance on a variety of complex control problems.
Deep reinforcement learning with successor features for navigation across similar environments
TLDR
This paper proposes a successor-feature-based deep reinforcement learning algorithm that can learn to transfer knowledge from previously mastered navigation tasks to new problem instances and substantially decreases the required learning time after the first task instance has been solved.
Information processing in echo state networks at the edge of chaos
TLDR
Evidence is presented that both information transfer and storage in the recurrent layer are maximized close to this phase transition, providing an explanation for why guiding the recurrent layers toward the edge of chaos is computationally useful.
Uncertainty-driven Imagination for Continuous Deep Reinforcement Learning
TLDR
The main incentive of this work is to keep the advantages of model-free Q-learning while minimizing real-world interaction by the employment of a dynamics model learned in parallel, to counteract adverse effects of imaginary rollouts with an inaccurate model.
Machine-learning-based diagnostics of EEG pathology
Approximate real-time optimal control based on sparse Gaussian process models
TLDR
This paper jointly learns a non-parametric model of the system dynamics - based on Gaussian Process Regression - and performs receding horizon control using an adapted iterative LQR formulation that results in an extremely data-efficient learning algorithm that can operate under real-time constraints.
Neural SLAM: Learning to Explore with External Memory
TLDR
This work embeds procedures mimicking that of traditional Simultaneous Localization and Mapping (SLAM) into the soft attention based addressing of external memory architectures, in which the external memory acts as an internal representation of the environment.
High-level Decision Making for Safe and Reasonable Autonomous Lane Changing using Reinforcement Learning
TLDR
A deep reinforcement learning (RL) agent is let to drive as close as possible to a desired velocity by executing reasonable lane changes on simulated highways with an arbitrary number of lanes by making use of a minimal state representation and a Deep Q-Network.
A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
TLDR
This survey focuses on deep learning solutions that target learning control policies for robotics applications, and discusses the two main paradigms for learning control with deep networks: deep reinforcement learning and imitation learning.
VR-Goggles for Robots: Real-to-Sim Domain Adaptation for Visual Control
TLDR
This letter proposes a simple yet effective shift loss that is agnostic to the downstream task, to constrain the consistency between subsequent frames which is important for consistent policy outputs, and validate the shift loss for artistic style transfer for videos and domain adaptation.
...
...