Marc P. Deisenroth

Latest

Learning Dynamic Tasks on a Large-scale Soft Robot in a Handful of Trials
Scalable Interpolation of Satellite Altimetry Data with Probabilistic Machine Learning
Co-located OLCI Optical Imagery and SAR Altimetry from Sentinel-3 for Enhanced Arctic Spring Sea Ice Surface Classification
Plasma Surrogate Modelling using Fourier Neural Operators
A Unifying Variational Framework for Gaussian Process Motion Planning
Interpretable Deep Gaussian Processes for Geospatial Tasks
Scalable Data Assimilation with Message Passing
Thin and Deep Gaussian Processes
Neural Field Movement Primitives for Joint Modelling of Scenes and Motions
Sliding Touch-based Exploration for Modeling Unknown Object Shape with Multi-finger Hands
Safe Trajectory Sampling in Model-based Reinforcement Learning
Faster Training of Neural ODEs Using Gauß–Legendre Quadrature
Understanding Deep Generative Models with Generalized Empirical Likelihoods
Optimal Transport for Offline Imitation Learning
Actually Sparse Variational Gaussian Processes
Optimal Transport for Offline Imitation Learning
Short-term Prediction and Filtering of Solar Power Using State-Space Gaussian Processes
One-Shot Transfer of Affordance Regions? AffCorrs!
Enhanced GPIS Learning Based on Local and Global Focus Areas
The Graph Cut Kernel for Ranked Data
Iterative State Estimation in Non-linear Dynamical Systems Using Approximate Expectation Propagation
Cauchy-Schwarz Regularized Autoencoder
Bayesian Optimization based Nonlinear Adaptive PID Design for Robust Control of the Joints at Mobile Manipulators
Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels
Pathwise Conditioning of Gaussian Processes
Aligning Time Series on Incomparable Spaces
Learning Contact Dynamics using Physically Structured Neural Networks
Matérn Gaussian Processes on Graphs
GPflux: A Library for Deep Gaussian Processes
Matérn Gaussian Processes on Riemannian Manifolds
High-Dimensional Bayesian Optimization with Manifold Gaussian Processes
A Foliated View of Transfer Learning
Probabilistic Active Meta-Learning
Estimating Barycenters of Measures in High Dimensions
Efficiently Sampling Functions from Gaussian Process Posteriors
Stochastic Differential Equations with Variational Wishart Diffusions
Aligning Time Series on Incomparable Spaces
Variational Integrator Networks for Physically Structured Embeddings
Mathematics for Machine Learning
High-Dimensional Bayesian Optimization with Projections using Quantile Gaussian Processes
Healing Products of Gaussian Process Experts
Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms
Deep Gaussian Processes with Importance-Weighted Variational Inference
Accelerating the BSM Interpretation of LHC Data with Machine Learning
GPdoemd: A Python Package for Design of Experiments for Model Discrimination
High-Dimensional Bayesian Optimization Using Low-Dimensional Feature Spaces
Variational Integrator Networks
Maximizing Acquisition Functions for Bayesian Optimization
Orthogonally Decoupled Variational Gaussian Processes
Meta Reinforcement Learning with Latent Variable Gaussian Processes
Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control
Bayesian Multi-Objective Optimisation with Mixed Analytical and Black-Box Functions: Application to Tissue Engineering
Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches
Gaussian Process Conditional Density Estimation
Real-Time Community Detection in Full Social Networks on a Laptop
Doubly Stochastic Variational Inference for Deep Gaussian Processes
A Brief Survey of Deep Reinforcement Learning
Bayesian Multi-Objective Optimisation of Neotissue Growth in a Perfusion Bioreactor Set-up
Customer Life Time Value Prediction Using Embeddings
Deeply Non-Stationary Gaussian Processes
Gaussian Process Domain Experts for Modeling of Facial Affect
Identification of Gaussian Process State Space Models
Model-based Contextual Policy Search for Data-Efficient Generalization of Robot Skills
Neural Embeddings of Graphs in Hyperbolic Space
Probabilistic Inference of Twitter Users' Age based on What They Follow
The Reparameterization Trick for Acquisition Functions
Resource-Constrained Decentralized Active Sensing using Distributed Gaussian Processes for Multi-Robots
Bayesian Optimization for Learning Gaits under Uncertainty
Bayesian Optimization with Dimension Scheduling: Application to Biological Systems
Gaussian Process Multiclass Classification with Dirichlet Priors for Imbalanced Data
Knowledge Transfer in Automatic Optimisation of Reconfigurable Designs
Manifold Gaussian Processes for Regression
Patch Kernels for Gaussian Processes in High-Dimensional Imaging Problems
Real-Time Community Detection in Large Social Networks on a Laptop
Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units
Data-efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models
Distributed Gaussian Processes
From Pixels to Torques: Policy Learning with Deep Dynamical Models
Gaussian Processes for Data-Efficient Learning in Robotics and Control
Learning Deep Dynamical Models From Image Pixels
Learning Inverse Dynamics Models with Contacts
Learning Torque Control in Presence of Contacts using Tactile Sensing from Robot Skin
Robust Bayesian Committee Machine for Large-Scale Gaussian Processes
An Experimental Evaluation of Bayesian Optimization on Bipedal Locomotion
Approximate Inference for Long-Term Forecasting with Periodic Gaussian Processes
Bayesian Gait Optimization for Bipedal Locomotion
Learning Deep Dynamical Models From Image Pixels
Model-based Inverse Reinforcement Learning
Multi-Modal Filtering for Non-linear Estimation
Multi-Task Policy Search for Robotics
Pareto Front Modeling for Sensitivity Analysis in Multi-Objective Bayesian Optimization
Policy Search For Learning Robot Control Using Sparse Data
A Survey on Policy Search for Robotics
Addressing the Correspondence Problem by Model-based Imitation Learning
An Experimental Evaluation of Bayesian Optimization on Bipedal Locomotion
Data-Efficient Generalization of Robot Skills with Contextual Policy Search
Feedback Error Learning for Rhythmic Motor Primitives
Hierarchical Learning of Motor Skills with Information-Theoretic Policy Search
Imitation Learning by Model-based Probabilistic Trajectory Matching
Model-based Imitation Learning by Probabilistic Trajectory Matching
Probabilistic Model-based Imitation Learning
Probabilistic Movement Modeling for Intention-based Decision Making
Expectation Propagation in Gaussian Process Dynamical Systems
Autonomous Planning and Control with Bayesian Nonparametric Models
Learning Deep Belief Networks from Non-Stationary Streams
Probabilistic Modeling of Human Dynamics for Intention Inference
Proceedings of the 10th European Workshop on Reinforcement Learning
Robust Filtering and Smoothing with Gaussian Processes
Solving Nonlinear Continuous State-Action-Observation POMDPs for Mechanical Systems with Gaussian Noise
Toward Fast Policy Search for Learning Legged Locomotion
A General Perspective on Gaussian Filtering and Smoothing: Explaining Current and Deriving New Algorithms
Gambit: An Autonomous Chess-Playing Robotic System
Learning in Robotics using Bayesian Nonparametrics
Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning
Multiple-Target Reinforcement Learning with a Single Policy
PILCO: A Model-Based and Data-Efficient Approach to Policy Search
Efficient Reinforcement Learning using Gaussian Processes
State-Space Inference and Learning with Gaussian Processes
Analytic Moment-based Gaussian Process Filtering
Bayesian Inference for Efficient Learning in Control
Efficient Reinforcement Learning for Motor Control
Efficient Reinforcement Learning using Gaussian Processes
Gaussian Process Dynamic Programming
Approximate Dynamic Programming with Gaussian Processes
Model-Based Reinforcement Learning with Continuous States and Actions
Probabilistic Inference for Fast Learning in Control
Online-Computation Approach to Optimal Control of Noise-Affected Nonlinear Systems with Continuous State and Control Spaces
An Online Computation Approach to Optimal Finite-Horizon Control of Nonlinear Stochastic Systems
Finite-Horizon Optimal State Feedback Control of Nonlinear Stochastic Systems Based on a Minimum Principle
Toward Optimal Control of Nonlinear Systems with Continuous State Spaces