Skip to content
conftrace_

policy switching cost

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

variance estimators (1) reference-advantage decomposition (1) gap-dependent bound (1) sub-optimality gap (1) regret bound (1) markov decision process (1) q-learning (1) regret analysis (1)

Papers

Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition ICLR 2025