A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints

no code implementations • 27 Apr 2023 • Jacopo Germano, Francesco Emanuele Stradi, Gianmarco Genalti, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti

We study online learning in episodic constrained Markov decision processes (CMDPs), where the goal of the learner is to collect as much reward as possible over the episodes, while guaranteeing that some long-term constraints are satisfied during the learning process.

Autonomous Driving Recommendation Systems