Data-driven regularized least squares with self-normalized bounds and lattice abstraction yields certified (N, ε)-PCIS for linear MDPs via conservative backward recursion.
Safe reinforcement learning in constrained markov decision processes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Data-Driven Synthesis of Probabilistic Controlled Invariant Sets for Linear MDPs
Data-driven regularized least squares with self-normalized bounds and lattice abstraction yields certified (N, ε)-PCIS for linear MDPs via conservative backward recursion.