SAMBA: safe model-based \& active reinforcement learning

DOI10.1007/s10994-021-06103-6OpenAlexW4211202104MaRDI QIDQ2127227

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

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

Gaussian processactive learningsafe reinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

HEBO: An Empirical Study of Assumptions in Bayesian Optimisation

Uses Software

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

Cites Work

• Provably safe and robust learning-based model predictive control
• MOGPTK
• Safety Gym
• CURL
• Robust model predictive control of constrained linear systems with bounded disturbances
• Policy Gradients for CVaR-Constrained MDPs
• Risk-Constrained Reinforcement Learning with Percentile Risk Criteria
• A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
• Nonlinear Lagrangian theory for nonconvex optimization.
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

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