382 citations · 1.2k across the 106 of their papers we have counts for
6 papers · 1 filter
Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
Hamish Flynn, David Reeb, Melih Kandemir +1
We present improved algorithms with worst-case regret guarantees for the stochastic linear bandit problem. The widely used "optimism in the face of uncertainty" principle reduces a…
An Upper Bound of the Bias of Nadaraya-Watson Kernel Regression under Lipschitz Assumptions
Samuele Tosatto, Riad Akrour, Jan Peters
The Nadaraya-Watson kernel estimator is among the most popular nonparameteric regression technique thanks to its simplicity. Its asymptotic bias has been studied by Rosenblatt in 1…
Probabilistic Trajectory Segmentation by Means of Hierarchical Dirichlet Process Switching Linear Dynamical Systems
Maximilian Sieb, Matthias Schultheis, Sebastian Szelag +2
Using movement primitive libraries is an effective means to enable robots to solve more complex tasks. In order to build these movement libraries, current algorithms require a prio…
Policy Search with High-Dimensional Context Variables
Voot Tangkaratt, Herke van Hoof, Simone Parisi +3
Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning…
Manifold Gaussian Processes for Regression
Roberto Calandra, Jan Peters, Carl Edward Rasmussen +1
Off-the-shelf Gaussian Process (GP) covariance functions encode smoothness assumptions on the structure of the function to be modeled. To model complex and non-differentiable funct…
Multi-Task Policy Search
Marc Peter Deisenroth, Peter Englert, Jan Peters +1
Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for ever…