An LP-based RL algorithm that identifies a small optimal basis and then resolves the corresponding linear equations adaptively, achieving an instance-dependent ~O(1/N) suboptimality gap for favorable instances.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive Resolving Methods for Reinforcement Learning with Function Approximations
An LP-based RL algorithm that identifies a small optimal basis and then resolves the corresponding linear equations adaptively, achieving an instance-dependent ~O(1/N) suboptimality gap for favorable instances.