• Publications
  • Influence
PILCO: A Model-Based and Data-Efficient Approach to Policy Search
TLDR
We introduce PILCO, a practical, data-efficient model-based policy search method for learning from scratch in only a few trials. Expand
A Survey on Policy Search for Robotics
TLDR
Policy search is a subfield in reinforcement learning which focuses on finding good parameters for a given policy parametrization. Expand
Doubly Stochastic Variational Inference for Deep Gaussian Processes
TLDR
We present a doubly stochastic variational inference algorithm for inference in DGP models that does not force independence or Gaussianity between layers. Expand
Gaussian Processes for Data-Efficient Learning in Robotics and Control
TLDR
We learn a probabilistic, non-parametric Gaussian process transition model of the system. Expand
Deep Reinforcement Learning: A Brief Survey
TLDR
Deep reinforcement learning (RL) is poised to revolutionize the field of artificial intelligence (AI) and represents a step toward building autonomous systems with a higherlevel understanding of the visual world. Expand
Distributed Gaussian Processes
TLDR
We introduce the robust Bayesian Committee Machine (rBCM), a practical and scalable product-of-experts model for large-scale distributed GP regression. Expand
A Brief Survey of Deep Reinforcement Learning
TLDR
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Expand
Efficient reinforcement learning using Gaussian processes
TLDR
We introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. Expand
Analytic moment-based Gaussian process filtering
TLDR
We propose an analytic moment-based filter for nonlinear stochastic dynamic systems modeled by Gaussian processes. Expand
Manifold Gaussian Processes for regression
TLDR
We propose Manifold Gaussian Processes, a novel supervised method that jointly learns a transformation of the data into a feature space and a GP regression from the feature space to observed space. Expand
...
1
2
3
4
5
...