Generalizing the operation of robots in dynamical environments regardless of the task complexity is one of the ultimate goals of robotics researchers. Learning from demonstration approaches supported by transfer learning and user feedback offer a …
A talk about how hierarchical acquisition functions can improve the performance of Bayesian Optimization on complex problems.
A workshop talk about how meta-parameters, required for most mapping algorithms, can be learned.
Learning control policies in robotic tasks requires a large number of interactions due to small learning rates, bounds on the updates or unknown constraints. In contrast humans can infer protective and safe solutions after a single failure or …
Tuning parameters is crucial for the performance of localization and mapping algorithms. In general, the tuning of the parameters requires expert knowledge and is sensitive to information about the structure of the environment. In order to design …
Gradient-free reinforcement learning algorithms often fail to scale to high dimensions and require a large number of rollouts. In this paper, we propose learning a predictor model that allows simulated rollouts in a rank-based black-box optimizer …
Abstract Bayesian Optimization is a powerful method to optimize black-box derivative-free functions, with high evaluation costs. For instance, applications can be found in the context of robotics, animation design or molecular design. However, Bayesian Optimization is not able to scale into higher dimensions, equivalent to optimizing more than 20 parameters. This thesis introduces HIBO, a new hierarchical algorithm in the context of high dimensional Bayesian Optimization. The algorithm uses an automatic feature generation.
Active transfer learning with neural networks through human-robot interactions.