Efficient Duple Perturbation Robustness in Low-rank MDPs.

Yang Hu Haitong Ma Bo Dai Na Li

Published in: CoRR (2024)

Keyphrases

low rank
matrix factorization
missing data
markov decision processes
semi supervised
linear combination
matrix completion
robust principal component analysis
singular value decomposition
high order
convex optimization
rank minimization
low rank matrix
trace norm
low rank matrices
reinforcement learning