feat: the rounds, states and state-action pairs of a stationary policy are Markov chains - #295

feat: the rounds, states and state-action pairs of a stationary policy are Markov chains#295

RemyDegenne wants to merge 1 commit into

LeanMachineLearning:mainLeanMachineLearning/LMLExplore:mainfrom

RemyDegenne:roadmap/markov-property-trajectory-essakine2026tight-reinforcementlearningRemyDegenne/LMLExplore:roadmap/markov-property-trajectory-essakine2026tight-reinforcementlearningCopy head branch name to clipboard