Introduces linear mixture distributionally robust MDPs and proves offline suboptimality bounds of order 1/sqrt(K) for TV, KL, and chi-squared uncertainty sets.
Model-based rein- forcement learning with value-targeted regression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
contest 1representative citing papers
citing papers explorer
-
Linear Mixture Distributionally Robust Markov Decision Processes
Introduces linear mixture distributionally robust MDPs and proves offline suboptimality bounds of order 1/sqrt(K) for TV, KL, and chi-squared uncertainty sets.