Constrained Cross-Entropy Method for Safe Reinforcement Learning

DOI10.1109/TAC.2020.3015931zbMATH Open1467.93153OpenAlexW3049652862MaRDI QIDQ5002124FDOQ5002124

Authors: M. Wen, Ufuk Topcu 

Publication date: 26 July 2021

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tac.2020.3015931

Mathematics Subject Classification ID

Existence theories for optimal control problems involving ordinary differential equations (49J15) Linear-quadratic optimal control problems (49N10) Control/observation systems governed by ordinary differential equations (93C15)

Cited In (1)

• Safety-constrained reinforcement learning with a distributional safety critic

This page was built for publication: Constrained Cross-Entropy Method for Safe Reinforcement Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5002124)