paper-with-me

홈 › Papers

The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation

2023-07-25 · Philip Amortila, Nan Jiang, Csaba Szepesvári

Theoretical guarantees in reinforcement learning (RL) are known to suffer multiplicative blow-up factors with respect to the misspecification error of function approximation. Yet, the nature of such \emph{approximation factors} -- especially their optimal form in a given learning problem -- is poorly understood. In this paper we study this question in linear off-policy value function estimation, where many open questions remain. We study the approximation factor in a broad spectrum of settings, such as with the weighted $L_2$-norm (where the weighting is the offline state distribution), the $L_\infty$ norm, the presence vs. absence of state aliasing, and full vs. partial coverage of the state space. We establish the optimal asymptotic approximation factors (up to constants) for all of these settings. In particular, our bounds identify two instance-dependent factors for the $L_2(\mu)$ norm and only one for the $L_\infty$ norm, which are shown to dictate the hardness of off-policy evaluation under misspecification.

📄 PDF Abstract BibTeX arXiv:2307.13332

Code (0)

등록된 구현이 없습니다.

Tasks

Off-policy evaluationReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error

2024-07-18 · Ally Yalei Du, Lin F. Yang, Ruosong Wang

The recent work by Dong & Yang (2023) showed for misspecified sparse linear bandits, one can obtain an $O\left(\epsilon\right)$-optimal policy using a polynomial number of samples when the sparsity is a constant, where $…

Q-Learning

Iterative Hierarchical Optimization for Misspecified Problems (IHOMP)

2016-02-10 · Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor

For complex, high-dimensional Markov Decision Processes (MDPs), it may be necessary to represent the policy with function approximation. A problem is misspecified whenever, the representation cannot express any policy wi…

On the Value of Interaction and Function Approximation in Imitation Learning

2021-12-01 · NeurIPS 2021 12 · Nived Rajaraman, Yanjun Han, Lin Yang, Jingbo Liu 외

We study the statistical guarantees for the Imitation Learning (IL) problem in episodic MDPs.Rajaraman et al. (2020) show an information theoretic lower bound that in the worst case, a learner which can even actively que…

Imitation LearningMulti-class Classification

Statistical Inference for Misspecified Contextual Bandits

2026-06-21 · Yongyi Guo, Ziping Xu arxiv

Contextual bandit algorithms have transformed modern experimentation by enabling real-time adaptation for personalized treatment. Yet these advantages create challenges for statistical inference due to adaptivity. We stu…

Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs

2023-10-13 · Debangshu Banerjee, Aditya Gopalan

Parametric, feature-based reward models are employed by a variety of algorithms in decision-making settings such as bandits and Markov decision processes (MDPs). The typical assumption under which the algorithms are anal…

Decision MakingMulti-Armed BanditsQ-Learning