Natural policy gradient primal-dual method for constrained Markov decision processes
Dong-Sheng Ding, Kaiqing Zhang, Tamer Başar, Mihailo R. Jovanović
2020Neural Information Processing Systems66 citations
Topics & Concepts
Dual (grammatical number)Markov decision processComputer scienceMathematical optimizationMarkov processMarkov chainMathematicsMachine learningStatisticsArtLiteratureReinforcement Learning in RoboticsAdvanced Bandit Algorithms ResearchAdvanced Control Systems Optimization