Reward Biased Maximum Likelihood Estimation for Learning in Constrained MDPs
classification
🧮 math.OC
keywords
biasedconstrainedestimationlearninglikelihoodmaximumrbmlereward
read the original abstract
We use the Reward Biased Maximum Likelihood Estimation (RBMLE) algorithm to learn optimal policies for constrained Markov Decision Processes (CMDPs). We analyze the learning regrets of RBMLE.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.