Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization

Open Webpage

Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti

Published: 01 Jan 2025, Last Modified: 14 May 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0