
A soft thumbsized visionbased sensor with accurate allround force perception
Visionbased haptic sensors have emerged as a promising approach to robo...
read it

Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains
A common approach to prediction and planning in partially observable dom...
read it

Planning from Pixels in Environments with Combinatorially Hard Search Spaces
The ability to form complex plans based on raw visual input is a litmus ...
read it

Selfsupervised Reinforcement Learning with Independently Controllable Subgoals
To successfully tackle challenging manipulation tasks, autonomous agents...
read it

Causal Influence Detection for Improving Efficiency in Reinforcement Learning
Many reinforcement learning (RL) environments consist of independent ent...
read it

Theory of Geometric Superresolution for Haptic Sensor Design
Haptic feedback is important to make robots more dexterous and effective...
read it

Assessing aesthetics of generated abstract images using correlation structure
Can we generate abstract aesthetic images without bias from natural or h...
read it

Informed Equation Learning
Distilling data into compact and interpretable analytic equations is one...
read it

CombOptNet: Fit the Right NPHard Problem by Learning Integer Programming Constraints
Bridging logical and algorithmic reasoning with modern machine learning ...
read it

The dynamical regime and its importance for evolvability, task performance and generalization
It has long been hypothesized that operating close to the critical state...
read it

Neuroalgorithmic Policies enable Fast Combinatorial Generalization
Although modelbased and modelfree approaches to learning the control o...
read it

Demystifying Inductive Biases for βVAE Based Architectures
The performance of βVariationalAutoencoders (βVAEs) and their variant...
read it

How to Train Your Differentiable Filter
In many robotic applications, it is crucial to maintain a belief about t...
read it

Selfsupervised Visual Reinforcement Learning with Objectcentric Representations
Autonomous agents need large repertoires of skills to act reasonably on ...
read it

Sampleefficient CrossEntropy Method for Realtime Planning
Trajectory optimizers for modelbased reinforcement learning, such as th...
read it

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
Building on recent progress at the intersection of combinatorial optimiz...
read it

Optimizing Rankbased Metrics with Blackbox Differentiation
Rankbased metrics are some of the most widely used criteria for perform...
read it

Differentiation of Blackbox Combinatorial Solvers
Achieving fusion of deep learning with combinatorial algorithms promises...
read it

Fast NonParametric Learning to Accelerate MixedInteger Programming for Online Hybrid Model Predictive Control
Today's fast linear algebra and numerical optimization tools have pushed...
read it

Analytical classical density functionals from an equation learning network
We explore the feasibility of using machine learning methods to obtain a...
read it

Control What You Can: Intrinsically Motivated TaskPlanning Agent
We present a novel intrinsically motivated agent that learns how to cont...
read it

Autonomous Identification and GoalDirected Invocation of EventPredictive Behavioral Primitives
Voluntary behavior of humans appears to be composed of small, elementary...
read it

Variational Autoencoders Pursue PCA Directions (by Accident)
The Variational Autoencoder (VAE) is a powerful architecture capable of ...
read it

Deep Reinforcement Learning for EventTriggered Control
Eventtriggered control (ETC) methods can achieve highperformance contr...
read it

Learning Equations for Extrapolation and Control
We present an approach to identify concise equations from data using a s...
read it

Extrapolation and learning equations
In classical machine learning, regression is treated as a black box proc...
read it