paper-with-me

홈 › Papers

Prolonged Learning and Hasty Stopping: the Wald Problem with Ambiguity

2022-08-30 · Sarah Auster, Yeon-Koo Che, Konrad Mierendorff

This paper studies sequential information acquisition by an ambiguity-averse decision maker (DM), who decides how long to collect information before taking an irreversible action. The agent optimizes against the worst-case belief and updates prior by prior. We show that the consideration of ambiguity gives rise to rich dynamics: compared to the Bayesian DM, the DM here tends to experiment excessively when facing modest uncertainty and, to counteract it, may stop experimenting prematurely when facing high uncertainty. In the latter case, the DM's stopping rule is non-monotonic in beliefs and features randomized stopping.

📄 PDF Abstract BibTeX arXiv:2208.14121

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Robust Exploratory Stopping under Ambiguity in Reinforcement Learning

2025-10-11 · Junyan Ye, Hoi Ying Wong, Kyunghyun Park arxiv

We propose and analyze a continuous-time robust reinforcement learning framework for optimal stopping under ambiguity. In this framework, an agent chooses a robust exploratory stopping time motivated by two objectives: r…

Reinforcement Learning

Optimal stopping and divestment timing under scenario ambiguity and learning

2024-08-18 · Andrea Mazzon, Peter Tankov

Aiming to analyze the impact of environmental transition on the value of assets and on asset stranding, we study optimal stopping and divestment timing decisions for an economic agent whose future revenues depend on the …

Decision Making

Optimal Stopping under Model Ambiguity: a Time-Consistent Equilibrium Approach

2019-06-04 · Yu-Jui Huang, Xiang Yu

An unconventional approach for optimal stopping under model ambiguity is introduced. Besides ambiguity itself, we take into account how ambiguity-averse an agent is. This inclusion of ambiguity attitude, via an $\alpha$-…

Decision Making

Early Stopping for Nonparametric Testing

2018-05-25 · NeurIPS 2018 12 · Meimei Liu, Guang Cheng

Early stopping of iterative algorithms is an algorithmic regularization method to avoid over-fitting in estimation and classification. In this paper, we show that early stopping can also be applied to obtain the minimax …

General Classification

Speed, Accuracy, and Complexity

2024-03-17 · Duarte Gonçalves

This paper re-examines the use of response time to infer problem complexity. It revisits a canonical Wald model of optimal stopping, taking signal-to-noise ratio as a measure of problem complexity. While choice quality i…