conftrace_

bellman completeness

4 papers

Explore in graph

Co-occurring keywords

sample complexity (1169) surprise bound (1) statistical complexity (6) value function realizability (1) concentrability coefficient (2) trajectory datum (26) linear mdp (34) regret bound (1926) bellman operator (29) polynomial-time algorithm (39)

Papers

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