
Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning
Reactive motion generation problems are usually solved by computing acti...
read it

Value Iteration in Continuous Actions, States and Time
Classical value iteration approaches are not applicable to environments ...
read it

Reinforcement Learning using Guided Observability
Due to recent breakthroughs, reinforcement learning (RL) has demonstrate...
read it

Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via RelativeEntropy Trust Regions
Trajectory optimization and model predictive control are essential techn...
read it

SKID RAW: Skill Discovery from Raw Trajectories
Integrating robots in complex everyday environments requires a multitude...
read it

Model Predictive ActorCritic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning
Substantial advancements to modelbased reinforcement learning algorithm...
read it

Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk
Discretetime stochastic optimal control remains a challenging problem f...
read it

Extended Task and Motion Planning of Longhorizon Robot Manipulation
Task and Motion Planning (TAMP) requires the integration of symbolic rea...
read it

Learning Humanlike Hand Reaching for HumanRobot Handshaking
One of the first and foremost nonverbal interactions that humans perfor...
read it

A Probabilistic Interpretation of SelfPaced Learning with Applications to Reinforcement Learning
Across machine learning, the use of curricula has shown strong empirical...
read it

HumanRobot Handshaking: A Review
For some years now, the use of social, anthropomorphic robots in various...
read it

Structured Policy Representation: Imposing Stability in arbitrarily conditioned dynamic systems
We present a new family of deep neural networkbased dynamic systems. Th...
read it

Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshop
This report presents the debates, posters, and discussions of the Sim2Re...
read it

Convex Optimization with an Interpolationbased Projection and its Application to Deep Learning
Convex optimizers have known many applications as differentiable layers ...
read it

A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning
Probabilistic regression techniques in control and robotics applications...
read it

Differentiable Physics Models for Realworld Offline Modelbased Reinforcement Learning
A limitation of modelbased reinforcement learning (MBRL) is the exploit...
read it

Batch Reinforcement Learning with a Nonparametric OffPolicy Policy Gradient
Offpolicy Reinforcement Learning (RL) holds the promise of better data ...
read it

Contextual LatentMovements OffPolicy Optimization for Robotic Manipulation Skills
Parameterized movement primitives have been extensively used for imitati...
read it

High Acceleration Reinforcement Learning for RealWorld Juggling with Binary Rewards
Robots that can learn in the physical world will be important to enable...
read it

ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows
We introduce ImitationFlow, a novel Deep generative model that allows le...
read it

A Differentiable Newton Euler Algorithm for Multibody Model Learning
In this work, we examine a spectrum of hybrid model for the domain of mu...
read it

Differentiable Implicit Layers
In this paper, we introduce an efficient backpropagation scheme for non...
read it

Active Inference or Control as Inference? A Unifying View
Active inference (AI) is a persuasive theoretical framework from computa...
read it

Advances in HumanRobot Handshaking
The use of social, anthropomorphic robots to support humans in various i...
read it

Assisted Teleoperation in Changing Environments with a Mixture of Virtual Guides
Haptic guidance is a powerful technique to combine the strengths of huma...
read it

ModelBased QualityDiversity Search for Efficient Robot Learning
Despite recent progress in robot learning, it still remains a challenge ...
read it

MultiSensor NextBestView Planning as MatroidConstrained Submodular Maximization
3D scene models are useful in robotics for tasks such as path planning, ...
read it

Convex Regularization in MonteCarlo Tree Search
MonteCarlo planning and Reinforcement Learning (RL) are essential to se...
read it

Deterministic Inference of Neural Stochastic Differential Equations
Model noise is known to have detrimental effects on neural networks, suc...
read it

Learning to Play Table Tennis From Scratch using Muscular Robots
Dynamic tasks like table tennis are relatively easy to learn for humans ...
read it

Reinforcement Learning from a Mixture of Interpretable Experts
Reinforcement learning (RL) has demonstrated its ability to solve high d...
read it

Orientation Attentive Robot Grasp Synthesis
Physical neighborhoods of grasping points in common objects may offer a ...
read it

Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation
The control of nonlinear dynamical systems remains a major challenge for...
read it

SelfPaced Deep Reinforcement Learning
Generalization and reuse of agent behaviour across a variety of learning...
read it

Deep Reinforcement Learning with Weighted QLearning
Overestimation of the maximum actionvalue is a wellknown problem that ...
read it

Learning to Fly via Deep ModelBased Reinforcement Learning
Learning to control robots without requiring models has been a longterm...
read it

Deep Adversarial Reinforcement Learning for Object Disentangling
Deep learning in combination with improved training techniques and high ...
read it

Bayesian Domain Randomization for SimtoReal Transfer
When learning policies for robot control, the realworld data required i...
read it

Underactuated Waypoint Trajectory Optimization for Light Painting Photography
Despite their abundance in robotics and nature, underactuated systems re...
read it

Dimensionality Reduction of Movement Primitives in Parameter Space
Movement primitives are an important policy class for realworld robotic...
read it

Probabilistic approach to physical object disentangling
Physically disentangling entangled objects from each other is a problem ...
read it

MetricBased Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms
The development of autonomous robotic systems that can learn from human ...
read it

An Upper Bound of the Bias of NadarayaWatson Kernel Regression under Lipschitz Assumptions
The NadarayaWatson kernel estimator is among the most popular nonparame...
read it

Evaluation of the Handshake Turing Test for anthropomorphic Robots
Handshakes are fundamental and common greeting and parting gestures amon...
read it

A Probabilistic Framework for Imitating Human Race Driver Behavior
Understanding and modeling human driver behavior is crucial for advanced...
read it

A Nonparametric Offpolicy Policy Gradient
Reinforcement learning (RL) algorithms still suffer from high sample com...
read it

MushroomRL: Simplifying Reinforcement Learning Research
MushroomRL is an opensource Python library developed to simplify the pr...
read it

LongTerm Visitation Value for Deep Exploration in Sparse Reward Reinforcement Learning
Reinforcement learning with sparse rewards is still an open challenge. C...
read it

Generalized Mean Estimation in MonteCarlo Tree Search
We consider MonteCarlo Tree Search (MCTS) applied to Markov Decision Pr...
read it

Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer
A key feature of intelligent behavior is the ability to learn abstract s...
read it
Jan Peters
is this you? claim profile