Login / Signup
An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-MDP.
Gianluca Drappo
Alberto Maria Metelli
Marcello Restelli
Published in:
Trans. Mach. Learn. Res. (2023)
Keyphrases
</>
regret minimization
finite horizon
markov decision processes
optimal policy
markov decision process
multistage
policy iteration
learning algorithm
infinite horizon
state space
sufficient conditions
game theoretic
average cost
inventory models
optimal stopping