Weighted-Norm Bounds on Model Approximation in MDPs with Unbounded Per-Step Cost.

Berk Bozkurt Aditya Mahajan Ashutosh Nayyar Yi Ouyang

Published in: CDC (2023)

Keyphrases

computational model
mathematical model
neural network
objective function
lower bound
prior knowledge
reinforcement learning
probabilistic model
probability distribution
statistical model
markov decision processes
error bounds
approximation algorithms
approximation methods