SAMBA: safe model-based \& active reinforcement learning

DOI10.1007/S10994-021-06103-6MaRDI QIDQ2127227zbMATH OpenOpenAlexFDO

Authors Alexander I. Cowen-Rivers, Daniel Palenicek, Vincent Moens, Mohammed Abdullah, Aivar Sootla, Jun Wang, Haitham Bou-Ammar

Publication date 20 April 2022

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2006.09436

zbMATH Keywords

active learningGaussian processsafe reinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
• CURL
• scientific article; zbMATH DE number 1348599 (Why is no real title available?)
• MOGPTK
• Near-optimal sensor placements in Gaussian processes: theory, efficient algorithms and empirical studies
• Nonlinear Lagrangian theory for nonconvex optimization.
• Nonlinear systems.
• Policy gradients for CVaR-constrained MDPs
• Provably safe and robust learning-based model predictive control
• Reinforcement learning. An introduction
• Risk-constrained reinforcement learning with percentile risk criteria
• Robust model predictive control of constrained linear systems with bounded disturbances
• Safety Gym

Cited in

(1)

• HEBO: An Empirical Study of Assumptions in Bayesian Optimisation

Describes a project that uses

Uses Software

• Safety Gym
• MOGPTK
• CURL
• SafePILCO
• PyTorch
• PILCO
• GPyTorch
• OpenAI Gym

This page was built for publication: SAMBA: safe model-based \& active reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2127227)