Introduces Good Policy Identification (GPI) and BEE-GPI algorithm whose sample complexity for positive instances has log(1/δ) coefficient O(H²/(V*−μ0)²) independent of state and action space sizes.
Advances in neural information processing systems , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
An actor-critic RL algorithm for low-rank MDPs achieves improved sample efficiency using solely a policy evaluation oracle.
citing papers explorer
-
Pure Exploration for a Good Policy in Reinforcement Learning with Bandit Feedback
Introduces Good Policy Identification (GPI) and BEE-GPI algorithm whose sample complexity for positive instances has log(1/δ) coefficient O(H²/(V*−μ0)²) independent of state and action space sizes.
-
Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs
An actor-critic RL algorithm for low-rank MDPs achieves improved sample efficiency using solely a policy evaluation oracle.