Safe Exploration for Active Learning with Gaussian Processes
By J. Schreiter, Duy Nguyen-Tuong, Mona Eberts, Bastian Bischoff, Heiner Markert, Marc Toussaint. 2015
116 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Angela P. Schoellig
- Andreas Krause
- Felix Berkenkamp
- Matteo Turchetta
- Péter Englert
- Marc Toussaint
- Sergey Levine
- Jan Peters
In Control and Systems Engineering
- Andreas Krause
- Felix Berkenkamp
- Angela P. Schoellig
- Matteo Turchetta
- Péter Englert
- Marc Toussaint
- Sergey Levine
- Marc Peter Deisenroth
Citations in the corpus
- Safe Model-based Reinforcement Learning with Stability Guarantees (2017, background): “The algorithms in [17] and [18] provide high-probability safety guarantees for any parameter that is evaluated on the real system.”
- Learning manipulation skills from a single demonstration (2018, methodology): “Schreiter et al. (2015) propose a safe exploration strategy for a similar problem to ours.”
- Safe controller optimization for quadrotors with Gaussian processes (2015, background): “In particular, it works well for expanding the safe set [20],”
- Safe Exploration in Finite Markov Decision Processes with Gaussian Processes (2016, background): “The corresponding GP posterior distribution over the unknown function is used to guide evaluations to informative locations.”