Tensor Low-Rank Approximation of Finite-Horizon Value Functions.

Sergio Rozada Antonio G. Marques

Published in: ICASSP (2024)

Keyphrases

finite horizon
low rank approximation
optimal policy
infinite horizon
markov decision processes
high order
multistage
long run
markov decision process
singular value decomposition
higher order
low rank
subspace learning
spectral clustering
average cost
markov chain
dimensionality reduction