November 03, 2020
We study the exploration problem with approximate linear action-value functions in episodic reinforcement learning under the notion of low inherent Bellman error, a condition normally employed to show convergence of approximate value iteration. First we relate this condition to other common frameworks and show that it is strictly more general than the low rank (or linear) MDP assumption of prior work. Second we provide an algorithm with a high probability regret bound $\widetilde O(\sum_{t=1}^H d_t \sqrt{K} + \sum_{t=1}^H \sqrt{d_t} \IBE K)$ where H is the horizon, K is the number of episodes, $\IBE$ is the value if the inherent Bellman error and dt is the feature dimension at timestep t. In addition, we show that the result is unimprovable beyond constants and logs by showing a matching lower bound. This has two important consequences: 1) it shows that exploration is possible using only \emph{batch assumptions} with an algorithm that achieves the optimal statistical rate for the setting we consider, which is more general than prior work on low-rank MDPs 2) the lack of closedness (measured by the inherent Bellman error) is only amplified by dt‾‾√ despite working in the online setting. Finally, the algorithm reduces to the celebrated \textsc{LinUCB} when H=1 but with a different choice of the exploration parameter that allows handling misspecified contextual linear bandits. While computational tractability questions remain open for the MDP setting, this enriches the class of MDPs with a linear representation for the action-value function where statistically efficient reinforcement learning is possible.
Written by
Alessandro Lazaric
Andrea Zanette
Emma Brunskill
Mykel Kochenderfer
Publisher
ICML
July 17, 2026
Zilin Xiao, Qi Ma, Jason Chen, Xintao Chen, Avinash Atreya, Hanjie Chen, Vicente Ordonez
July 17, 2026
July 13, 2026
Xiaodong Wang, Xuanyi Zhao, Pedro Rodriguez, Devendra Singh Sachan, Barlas Oguz, Seungwhan Moon, Shang-Wen Li, Gargi Ghosh, Xin Dong, Wen-Tau Yih
July 13, 2026
July 03, 2026
Sonia Joseph, Quentin Garrido, Randall Balestriero, Matthew Kowal, Thomas Fel, Shahab Bakhtiari, Blake Richards, Mike Rabbat
July 03, 2026
June 05, 2026
Zeyu Yang, Qi Ma, Jason Chen, Anshumali Shrivastava
June 05, 2026

Our approach
Latest news
Foundational models