Search Results for author:
Found 66 papers, 30 papers with code
Learning with 3D rotations, a hitchhiker's guide to SO(3)
Many settings in machine learning require the selection of a rotation representation.
Wild Visual Navigation: Fast Traversability Learning via Pre-Trained Models and Online Self-Supervision
Natural environments such as forests and grasslands are challenging for robotic navigation because of the false perception of rigid obstacles from high grass, twigs, or bushes.
Colored Noise in PPO: Improved Exploration and Performance Through Correlated Action Sampling
Proximal Policy Optimization (PPO), a popular on-policy deep reinforcement learning method, employs a stochastic policy for exploration.
Regularity as Intrinsic Reward for Free Play
Our generalized formulation of Regularity as Intrinsic Reward (RaIR) allows us to operationalize it within model-based reinforcement learning.
Multi-View Causal Representation Learning with Partial Observability
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities.
Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
We demonstrate the effectiveness of our method on a local navigation task where a quadruped robot needs to reach the target within a finite horizon.
Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
We find that for both tasks RNNs develop longer timescales with increasing $N$, but depending on the learning objective, they use different mechanisms.
Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning
We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and pessimism in the face of aleatoric uncertainty of an ensemble of stochastic neural networks. Various experiments indicate that the separation of uncertainties is essential to performing well with data-driven MPC approaches in uncertain and safety-critical control environments.
Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models
Humans excel at robust bipedal walking in complex natural environments.
Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World
For this reason, a large part of the reinforcement learning (RL) community uses simulators to develop and benchmark algorithms.
Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
To coordinate the efforts of the research community toward tackling this problem, we propose a benchmark including: i) a large collection of data for offline learning from a dexterous manipulation platform on two tasks, obtained with capable RL agents trained in simulation; ii) the option to execute learned policies on a real-world robotic system and a simulation for efficient debugging.
Diverse Offline Imitation Learning
There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity.
The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks
Biological cortical neurons are remarkably sophisticated computational devices, temporally integrating their vast synaptic input over an intricate dendritic tree, subject to complex, nonlinearly interacting internal biological processes.
Ranked #1 on
Time Series
on neuronIO
Locally adaptive cellular automata for goal-oriented self-organization
In this paper, we propose a new model class of adaptive cellular automata that allows for the generation of scalable and expressive models.
Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
Recently, it was shown that the reconstruction of pre-trained self-supervised features leads to object-centric representations on unconstrained real-world image datasets.
Discovering Causal Relations and Equations from Data
Discovering equations, laws and principles that are invariant, robust and causal explanations of the world has been fundamental in physical sciences throughout the centuries.
Inductive biases in deep learning models for weather prediction
We show how the design choices made in each of the five design elements relate to structural assumptions.
When to be critical? Performance and evolvability in different regimes of neural Ising agents
To test it we introduce a hard and simple task: for the hard task, agents evolve closer to criticality whereas more subcritical solutions are found for the simple task.
Efficient Learning of High Level Plans from Play
Real-world robotic manipulation tasks remain an elusive challenge, since they involve both fine-grained environment interaction, as well as the ability to plan for long-horizon goals.
Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
Learning diverse skills is one of the main challenges in robotics.
Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks
Humans are able to outperform robots in terms of robustness, versatility, and learning of new tasks in a wide variety of movements.
Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
Learning agile skills is one of the main challenges in robotics.
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation
It has been a long-standing dream to design artificial agents that explore their environment efficiently via intrinsic motivation, similar to how children perform curious free play.
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
Leveraging self-consistency, we show that the ELBO converges to a regularized log-likelihood.
Developing hierarchical anticipations via neural network-based event segmentation
Humans can make predictions on various time scales and hierarchical levels.
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
Muscle-actuated organisms are capable of learning an unparalleled diversity of dexterous movements despite their vast amount of muscles.
Backpropagation through Combinatorial Algorithms: Identity with Projection Works
Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities.
Ranked #1 on
Density Estimation
on MNIST
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
In this work, we examine this approach and identify potential hazards associated with the use of log-likelihood in conjunction with gradient-based optimizers.
Hierarchical Reinforcement Learning with Timed Subgoals
Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
A soft thumb-sized vision-based sensor with accurate all-round force perception
Insight has an overall spatial resolution of 0. 4 mm, force magnitude accuracy around 0. 03 N, and force direction accuracy around 5 degrees over a range of 0. 03--2 N for numerous distinct contacts with varying contact area.
Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains
A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hidden, task-relevant factors.
Planning from Pixels in Environments with Combinatorially Hard Search Spaces
The ability to form complex plans based on raw visual input is a litmus test for current capabilities of artificial intelligence, as it requires a seamless combination of visual processing and abstract algorithmic execution, two traditionally separate areas of computer science.
Self-supervised Reinforcement Learning with Independently Controllable Subgoals
We propose a novel self-supervised agent that estimates relations between environment components and uses them to independently control different parts of the environment state.
Causal Influence Detection for Improving Efficiency in Reinforcement Learning
Many reinforcement learning (RL) environments consist of independent entities that interact sparsely.
Assessing aesthetics of generated abstract images using correlation structure
We demonstrate that even with the randomly selected weights the correlation functions remain largely determined by the network architecture.
Informed Equation Learning
Our system then utilizes a robust method to learn equations with atomic functions exhibiting singularities, as e. g. logarithm and division.
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
Bridging logical and algorithmic reasoning with modern machine learning techniques is a fundamental challenge with potentially transformative impact.
The dynamical regime and its importance for evolvability, task performance and generalization
Surprisingly, we find that all populations, regardless of their initial regime, evolve to be subcritical in simple tasks and even strongly subcritical populations can reach comparable performance.
Neuro-algorithmic Policies enable Fast Combinatorial Generalization
Furthermore, we show that for a certain subclass of the MDP framework, this can be alleviated by neuro-algorithmic architectures.
Demystifying Inductive Biases for $β$-VAE Based Architectures
By small, elaborate perturbations of existing datasets, we hide the convenient correlation structure that is easily exploited by a variety of architectures.
Machine learning time-local generators of open quantum dynamics
Such evolution is typically emerging under the assumption of a weak coupling between the system and an infinitely large bath.
Quantum Physics Quantum Gases
Clearing the Path for Truly Semantic Representation Learning
The performance of $\beta$-Variational-Autoencoders ($\beta$-VAEs) and their variants on learning semantically meaningful, disentangled representations is unparalleled.
Extracting Strong Policies for Robotics Tasks from zero-order trajectory optimizers
Solving high-dimensional, continuous robotic tasks is a challenging optimization problem.
Neuro-algorithmic Policies for Discrete Planning
Although model-based and model-free approaches to learning control of systems have achieved impressive results on standard benchmarks, most have been shown to be lacking in their generalization capabilities.
How to Train Your Differentiable Filter
In many robotic applications, it is crucial to maintain a belief about the state of a system, which serves as input for planning and decision making and provides feedback during task execution.
Self-supervised Visual Reinforcement Learning with Object-centric Representations
We show that the structure in the representations in combination with goal-conditioned attention policies helps the autonomous agent to discover and learn useful skills.
Discrete Planning with Neuro-algorithmic Policies
Although model-based and model-free approaches to learning the control of systems have achieved impressive results on standard benchmarks, most have been shown to be lacking in their generalization capabilities.
Fit The Right NP-Hard Problem: End-to-end Learning of Integer Programming Constraints
Bridging logical and algorithmic reasoning with modern machine learning techniques is a fundamental challenge with potentially transformative impact.
Sample-efficient Cross-Entropy Method for Real-time Planning
However, their sampling inefficiency prevents them from being used for real-time planning and control.
Model-based Reinforcement Learning
reinforcement-learning
+1
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers.
Ranked #2 on
Graph Matching
on PASCAL VOC
Optimizing Rank-based Metrics with Blackbox Differentiation
Rank-based metrics are some of the most widely used criteria for performance evaluation of computer vision models.
Differentiation of Blackbox Combinatorial Solvers
Achieving fusion of deep learning with combinatorial algorithms promises transformative changes to artificial intelligence.
Fast Non-Parametric Learning to Accelerate Mixed-Integer Programming for Online Hybrid Model Predictive Control
Today's fast linear algebra and numerical optimization tools have pushed the frontier of model predictive control (MPC) forward, to the efficient control of highly nonlinear and hybrid systems.
Analytical classical density functionals from an equation learning network
We explore the feasibility of using machine learning methods to obtain an analytic form of the classical free energy functional for two model fluids, hard rods and Lennard--Jones, in one dimension .
Control What You Can: Intrinsically Motivated Task-Planning Agent
We present a novel intrinsically motivated agent that learns how to control the environment in the fastest possible manner by optimizing learning progress.
Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives
Here, we introduce a computational learning architecture, termed surprise-based behavioral modularization into event-predictive structures (SUBMODES), that explores behavior and identifies the underlying behavioral units completely from scratch.
Variational Autoencoders Pursue PCA Directions (by Accident)
The Variational Autoencoder (VAE) is a powerful architecture capable of representation learning and generative modeling.
Deep Reinforcement Learning for Event-Triggered Control
Event-triggered control (ETC) methods can achieve high-performance control with a significantly lower number of samples compared to usual, time-triggered methods.
Learning Equations for Extrapolation and Control
We present an approach to identify concise equations from data using a shallow neural network approach.
L4: Practical loss-based stepsize adaptation for deep learning
We propose a stepsize adaptation scheme for stochastic gradient descent.
Extrapolation and learning equations
In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs.
Self-organized control for musculoskeletal robots
The paper presents a solution with a controller that is devoid of any functionalities of its own, given by a fixed, explicit and context-free function of the recent history of the sensor values.
Quantifying Emergent Behavior of Autonomous Robots
For deterministic systems both measures will diverge with increasing resolution.
A novel plasticity rule can explain the development of sensorimotor intelligence
Grounding autonomous behavior in the nervous system is a fundamental challenge for neuroscience.
Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting: a critical analysis
Previous experiments have shown that the predictive information (PI) is a good candidate to support autonomous, open-ended learning of complex behaviours, because a maximisation of the PI corresponds to an exploration of morphology- and environment-dependent behavioural regularities.
Information driven self-organization of complex robotic behaviors
We study nonlinear and nonstationary systems and introduce the time-local predicting information (TiPI) which allows us to derive exact results together with explicit update rules for the parameters of the controller in the dynamical systems framework.
