conftrace_

bellman completeness

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

sample complexity (2) reinforcement learning (2) surprise bound (1) offline policy evaluation (1) statistical complexity (1) value function realizability (1) concentrability coefficient (1) polynomial time algorithm (1) trajectory data (1) linear mdp (1)

Papers

Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions COLT 2024 Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data COLT 2024 Provably Efficient Reinforcement Learning via Surprise Bound AISTATS 2023 When is Realizability Sufficient for Off-Policy Reinforcement Learning? ICML 2023