Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics
By Felix Berkenkamp, Andreas Krause, Angela P. Schoellig. Machine-mediated learning, 2016
364 citations recorded by the source corpus.
Selecting the right tuning parameters for algorithms is a pravelent problem in machine learning that can significantly affect the performance of algorithms. Data-efficient optimization algorithms, such as Bayesian optimization, have been used to automate this process. During experiments on real-world systems such as robotic platforms these methods can evaluate unsafe parameters that lead to safety-critical system failures and can destroy the system. Recently, a safe Bayesian optimization algorithm, called SafeOpt , has been developed, which guarantees that the performance of the system never falls below a critical value; that is, safety is defined based on the performance function. However, coupling performance and safety is often not desirable in practice, since they are often opposing objectives. In this paper, we present a generalized algorithm that allows for multiple safety constraints separate from the objective. Given an initial set of safe parameters, the algorithm maximizes performance but only evaluates parameters that satisfy safety for all constraints with high probability. To this end, it carefully explores the parameter space by exploiting regularity assumptions in terms of a Gaussian process prior. Moreover, we show how context variables can be used to safely transfer knowledge to new situations and tasks. We provide a theoretical analysis and demonstrate that the proposed algorithm enables fast, automatic, and safe optimization of tuning parameters in experiments on a quadrotor vehicle.
Subfields: Artificial Intelligence, Computational Theory and Mathematics, Control and Systems Engineering
View Paper: https://www.semanticscholar.org/paper/a6b82abf3bdc0a190bf21e290db70ac1091c9ff8
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
- Ruosong Wang
- Lin F. Yang
- Angela P. Schoellig
- Artur Dubrawski
- Lukas Brunke
- Yichong Xu
- Adam W. Hall
- Zhaocong Yuan
In Computational Theory and Mathematics
In Control and Systems Engineering
Citations in the corpus
- Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning (2021, background): “1 Nonlinear (69, 79, 82), GP (78, 79, 80, 81) NN (70, 75, 85, 86, 87), Tabular (73) Input & state (69, 70, 73, 75, 78, 79, 80, 81, 82) Trajectory (87) Input & state (69, 70, 73, 75, 78, 79, 80, 81, 82) Trajectory (85, 86, 87) Stabilization (81), Tracking (79), Navigation (69, 70, 73, 82, 85, 86), Lo”
- Preference-based Reinforcement Learning with Finite-Time Guarantees (2020, background): “However, in practice, reward functions might not be readily available or hard to design, and hand-crafted rewards might lead to undesired behaviors, like reward hacking [8, 1].”