[HTML][HTML] Evolutionary robotics: what, why, and where to

S Doncieux, N Bredeche, JB Mouret… - Frontiers in Robotics and …, 2015 - frontiersin.org
Evolutionary robotics applies the selection, variation, and heredity principles of natural
evolution to the design of robots with embodied intelligence. It can be considered as a …

Derivative-free reinforcement learning: A review

H Qian, Y Yu - Frontiers of Computer Science, 2021 - Springer
Reinforcement learning is about learning agent models that make the best sequential
decisions in unknown environments. In an unknown environment, the agent needs to …

Scalable bayesian optimization using deep neural networks

J Snoek, O Rippel, K Swersky, R Kiros… - International …, 2015 - proceedings.mlr.press
Bayesian optimization is an effective methodology for the global optimization of functions
with expensive evaluations. It relies on querying a distribution over functions defined by a …

Max-value entropy search for efficient Bayesian optimization

Z Wang, S Jegelka - International Conference on Machine …, 2017 - proceedings.mlr.press
Abstract Entropy Search (ES) and Predictive Entropy Search (PES) are popular and
empirically successful Bayesian Optimization techniques. Both rely on a compelling …

Robots that can adapt like animals

A Cully, J Clune, D Tarapore, JB Mouret - Nature, 2015 - nature.com
Robots have transformed many industries, most notably manufacturing, and have the power
to deliver tremendous benefits to society, such as in search and rescue, disaster response …

Bayesian optimization for learning gaits under uncertainty: An experimental comparison on a dynamic bipedal walker

R Calandra, A Seyfarth, J Peters… - Annals of Mathematics …, 2016 - Springer
Designing gaits and corresponding control policies is a key challenge in robot locomotion.
Even with a viable controller parametrization, finding near-optimal parameters can be …

Safe controller optimization for quadrotors with Gaussian processes

F Berkenkamp, AP Schoellig… - 2016 IEEE international …, 2016 - ieeexplore.ieee.org
One of the most fundamental problems when designing controllers for dynamic systems is
the tuning of the controller parameters. Typically, a model of the system is used to obtain an …

[HTML][HTML] Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics

F Berkenkamp, A Krause, AP Schoellig - Machine Learning, 2023 - Springer
Selecting the right tuning parameters for algorithms is a pravelent problem in machine
learning that can significantly affect the performance of algorithms. Data-efficient …

Virtual vs. real: Trading off simulations and physical experiments in reinforcement learning with Bayesian optimization

A Marco, F Berkenkamp, P Hennig… - … on Robotics and …, 2017 - ieeexplore.ieee.org
In practice, the parameters of control policies are often tuned manually. This is time-
consuming and frustrating. Reinforcement learning is a promising alternative that aims to …

Towards dynamic and safe configuration tuning for cloud databases

X Zhang, H Wu, Y Li, J Tan, F Li, B Cui - Proceedings of the 2022 …, 2022 - dl.acm.org
Configuration knobs of database systems are essential to achieve high throughput and low
latency. Recently, automatic tuning systems using machine learning methods (ML) have …