paper-with-me

홈 › Papers

Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs

2019-02-20 · NeurIPS 2019 12 · Marek Petrik, Reazul Hasan Russell

Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by the ambiguity set---the set of plausible transition probabilities---which is usually constructed as a multi-dimensional confidence region. Existing methods construct ambiguity sets as confidence regions using concentration inequalities which leads to overly conservative solutions. This paper proposes a new paradigm that can achieve better solutions with the same robustness guarantees without using confidence regions as ambiguity sets. To incorporate prior knowledge, our algorithms optimize the size and position of ambiguity sets using Bayesian inference. Our theoretical analysis shows the safety of the proposed method, and the empirical results demonstrate its practical promise.

📄 PDF Abstract BibTeX arXiv:1902.07605

Code (1)

marekpetrik/craam2 공식 구현

Tasks

Bayesian InferencePositionreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Tight Bayesian Ambiguity Sets for Robust MDPs

2018-11-15 · Reazul Hasan Russel, Marek Petrik

Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMDPs) to compute policies with provable wo…

Decision MakingReinforcement LearningReinforcement Learning (RL)Sequential Decision Making

CalPro: Prior-Aware Evidential--Conformal Prediction with Structure-Aware Guarantees for Protein Structures

2026-01-12 · Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma arxiv

Deep protein structure predictors such as AlphaFold provide confidence estimates (e.g., pLDDT) that are often miscalibrated and degrade under distribution shifts across experimental modalities, temporal changes, and intr…

Robust Partial 3D Point Cloud Registration via Confidence Estimation under Global Context

2025-09-29 · Yongqiang Wang, Weigang Li, Wenping Liu, Zhe Xu 외 arxiv

Partial point cloud registration is essential for autonomous perception and 3D scene understanding, yet it remains challenging owing to structural ambiguity, partial visibility, and noise. We address these issues by prop…

Point Cloud RegistrationScene Understanding

When Annotators Disagree, Topology Explains: Mapper, a Topological Tool for Exploring Text Embedding Geometry and Ambiguity

2025-10-20 · Nisrine Rair, Alban Goupil, Valeriu Vrabie, Emmanuel Chochoy arxiv

Language models are often evaluated with scalar metrics like accuracy, but such measures fail to capture how models internally represent ambiguity, especially when human annotators disagree. We propose a topological pers…

Randomized Gaussian Process Upper Confidence Bound with Tighter Bayesian Regret Bounds

2023-02-03 · Shion Takeno, Yu Inatsu, Masayuki Karasuyama

Gaussian process upper confidence bound (GP-UCB) is a theoretically promising approach for black-box optimization; however, the confidence parameter $\beta$ is considerably large in the theorem and chosen heuristically i…