English
Related papers

Related papers: Reward Selection with Noisy Observations

200 papers

We study the prophet inequality, a fundamental problem in online decision-making and optimal stopping, in a practical setting where rewards are observed only through noisy realizations and reward distributions are unknown. At each stage,…

Machine Learning · Statistics 2026-04-03 Jung-hun Kim , Vianney Perchet

Prophet inequality concerns a basic optimal stopping problem and states that simple threshold stopping policies -- i.e., accepting the first reward larger than a certain threshold -- can achieve tight $\frac{1}{2}$-approximation to the…

Computer Science and Game Theory · Computer Science 2024-10-31 Wei Tang , Haifeng Xu , Ruimin Zhang , Derek Zhu

In the classical optimal stopping problem, a player is given a sequence of random variables $X_1\ldots X_n$ with known distributions. After observing the realization of $X_i$, the player can either accept the observed reward from $X_i$ and…

Discrete Mathematics · Computer Science 2020-07-24 Shipra Agrawal , Jay Sethuraman , Xingyu Zhang

Online advertising has motivated interest in online selection problems. Displaying ads to the right users benefits both the platform (e.g., via pay-per-click) and the advertisers (by increasing their reach). In practice, not all users click…

Computer Science and Game Theory · Computer Science 2024-08-16 Sebastian Perez-Salazar , Mohit Singh , Alejandro Toriello

We take a unifying approach to single selection optimal stopping problems with random arrival order and independent sampling of items. In the problem we consider, a decision maker (DM) initially gets to sample each of $N$ items…

Computer Science and Game Theory · Computer Science 2021-08-11 José Correa , Andrés Cristi , Boris Epstein , José Soto

We introduce the \textit{prophet inequality with uncertain acceptance} model, in which a decision maker sequentially observes a sequence of independent options, each characterized by a value $x_i$ and an acceptance probability $p_i$, both…

Computer Science and Game Theory · Computer Science 2026-03-25 Emile Martinez , Felipe Garrido-Lucero , Umberto Grandi , Sebastian Pérez-Salazar

Natural and formal languages provide an effective mechanism for humans to specify instructions and reward functions. We investigate how to generate policies via RL when reward functions are specified in a symbolic language captured by…

Machine Learning · Computer Science 2022-11-24 Andrew C. Li , Zizhao Chen , Pashootan Vaezipoor , Toryn Q. Klassen , Rodrigo Toro Icarte , Sheila A. McIlraith

The I.I.D. Prophet Inequality is a fundamental problem where, given $n$ independent random variables $X_1,\dots,X_n$ drawn from a known distribution $\mathcal{D}$, one has to decide at every step $i$ whether to stop and accept $X_i$ or…

Computer Science and Game Theory · Computer Science 2024-12-02 Vasilis Livanos , Ruta Mehta

Motivated by applications where impatience is pervasive and evaluation times are uncertain, we study a selection model where options may expire at an unknown point in time and evaluation times are stochastic. Initially, the decision-maker…

Optimization and Control · Mathematics 2026-02-05 Yihua Xu , Rohan Ghuge , Sebastian Perez-Salazar

In a prophet inequality problem, $n$ independent random variables are presented to a gambler one by one. The gambler decides when to stop the sequence and obtains the most recent value as reward. We evaluate a stopping rule by the…

Data Structures and Algorithms · Computer Science 2023-11-16 Andrés Cristi , Bruno Ziliotto

Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before…

Machine Learning · Computer Science 2024-04-11 Guojian Wang , Faguo Wu , Xiao Zhang

In the classical prophet inequality, a gambler observes a sequence of stochastic rewards $V_1,...,V_n$ and must decide, for each reward $V_i$, whether to keep it and stop the game or to forfeit the reward forever and reveal the next value…

Data Structures and Algorithms · Computer Science 2013-07-16 Pablo D. Azar , Robert Kleinberg , S. Matthew Weinberg

Exploration is essential in reinforcement learning as an agent relies on trial and error to learn an optimal policy. However, when rewards are sparse, naive exploration strategies, like noise injection, are often insufficient. Intrinsic…

Machine Learning · Computer Science 2026-01-30 Minjae Cho , Huy Trong Tran

We study the problem of learning revenue-optimal multi-bidder auctions from samples when the samples of bidders' valuations can be adversarially corrupted or drawn from distributions that are adversarially perturbed. First, we prove tight…

Computer Science and Game Theory · Computer Science 2021-07-14 Wenshuo Guo , Michael I. Jordan , Manolis Zampetakis

We introduce a model of competing agents in a prophet setting, where rewards arrive online, and decisions are made immediately and irrevocably. The rewards are unknown from the outset, but they are drawn from a known probability…

Computer Science and Game Theory · Computer Science 2021-07-02 Tomer Ezra , Michal Feldman , Ron Kupfer

We investigate the problem of best policy identification in discounted linear Markov Decision Processes in the fixed confidence setting under a generative model. We first derive an instance-specific lower bound on the expected number of…

Machine Learning · Computer Science 2022-08-12 Jerome Taupin , Yassir Jedra , Alexandre Proutiere

We study the Pandora's Box problem in an online learning setting with semi-bandit feedback. In each round, the learner sequentially pays to open up to $n$ boxes with unknown reward distributions, observes rewards upon opening, and decides…

Machine Learning · Computer Science 2025-10-27 Junyan Liu , Ziyun Chen , Kun Wang , Haipeng Luo , Lillian J. Ratliff

Prophet inequalities for rewards maximization are fundamental to optimal stopping theory with extensive applications to mechanism design and online optimization. We study the \emph{cost minimization} counterpart of the classical prophet…

Computer Science and Game Theory · Computer Science 2023-02-24 Vasilis Livanos , Ruta Mehta

Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction. A typical rationalization criterion, i.e. maximum mutual…

Machine Learning · Computer Science 2020-03-24 Shiyu Chang , Yang Zhang , Mo Yu , Tommi S. Jaakkola

We study the i.i.d. $k$-selection prophet inequality problem, where a decision-maker sequentially observes $n$ independent nonnegative rewards and may accept at most $k$ of them without knowledge of future realizations. The objective is to…

Optimization and Control · Mathematics 2026-02-24 Jieming Kong , Karthyek Murthy
‹ Prev 1 2 3 10 Next ›