English
Related papers

Related papers: Sequential Decision Making with Expert Demonstrati…

200 papers

The advent of Generative Artificial Intelligence (GAI) has heralded an inflection point that changed how society thinks about knowledge acquisition. While GAI cannot be fully trusted for decision-making, it may still provide valuable…

Methodology · Statistics 2025-05-20 Sean O'Hagan , Veronika Ročková

In this paper, we consider the problem of estimating parameters in a linear regression model. We propose a sequential learning procedure to determine the sample size for achieving a given small estimation risk, under the widely used…

Methodology · Statistics 2023-11-07 Jun Hu , Yan Zhuang , Shunan Zhao

Offline imitation learning typically learns from expert and unlabeled demonstrations, yet often overlooks the valuable signal in explicitly undesirable behaviors. In this work, we study offline imitation learning from contrasting behaviors,…

Machine Learning · Computer Science 2025-05-28 Huy Hoang , Tien Mai , Pradeep Varakantham , Tanvi Verma

We cast episodic Markov decision process (MDP) planning as Bayesian inference over policies. A policy is treated as the latent variable and is assigned an unnormalized probability of optimality that is monotone in its expected return,…

Machine Learning · Computer Science 2026-04-14 David Tolpin

The exponential growth of volume, variety and velocity of data is raising the need for investigations of automated or semi-automated ways to extract useful patterns from the data. It requires deep expert knowledge and extensive…

Machine Learning · Computer Science 2020-07-22 Abbas Raza Ali , Marcin Budka , Bogdan Gabrys

In offline Imitation Learning (IL), one of the main challenges is the \textit{covariate shift} between the expert observations and the actual distribution encountered by the agent, because it is difficult to determine what action an agent…

Machine Learning · Computer Science 2024-06-19 Jie-Jing Shao , Hao-Sen Shi , Lan-Zhe Guo , Yu-Feng Li

We consider online learning problems under a partial observability model capturing situations where the information conveyed to the learner is between full information and bandit feedback. In the simplest variant, we assume that in addition…

Machine Learning · Computer Science 2026-04-28 Tomas Kocak , Gergely Neu , Michal Valko , Remi Munos

The ranking problem is to order a collection of units by some unobserved parameter, based on observations from the associated distribution. This problem arises naturally in a number of contexts, such as business, where we may want to rank…

Methodology · Statistics 2016-10-28 Toby Kenney , Hao He , Hong Gu

On a variety of complex decision-making tasks, from doctors prescribing treatment to judges setting bail, machine learning algorithms have been shown to outperform expert human judgments. One complication, however, is that it is often…

Methodology · Statistics 2018-05-07 Jongbin Jung , Ravi Shroff , Avi Feller , Sharad Goel

We analyze boundedly rational updating from aggregate statistics in a model with binary actions and binary states. Agents each take an irreversible action in sequence after observing the unordered set of previous actions. Each agent first…

Machine Learning · Computer Science 2021-01-11 Itai Arieli , Yakov Babichenko , Manuel Mueller-Frank

We consider a sequential learning problem with Gaussian payoffs and side information: after selecting an action $i$, the learner receives information about the payoff of every action $j$ in the form of Gaussian observations whose mean is…

Machine Learning · Statistics 2015-10-29 Yifan Wu , András György , Csaba Szepesvári

This paper proposes an algorithm for real-time learning without explicit feedback. The algorithm combines the ideas of semi-supervised learning on graphs and online learning. In particular, it iteratively builds a graphical representation…

Machine Learning · Computer Science 2026-05-01 Branislav Kveton , Michal Valko , Matthai Phillipose , Ling Huang

The deployment of Multi-Armed Bandits (MAB) has become commonplace in many economic applications. However, regret guarantees for even state-of-the-art linear bandit algorithms (such as Optimism in the Face of Uncertainty Linear bandit…

Econometrics · Economics 2023-02-28 Jingwen Zhang , Yifang Chen , Amandeep Singh

Objective prior distributions represent an important tool that allows one to have the advantages of using the Bayesian framework even when information about the parameters of a model is not available. The usual objective approaches work off…

Methodology · Statistics 2018-09-25 Fabrizio Leisen , Cristiano Villa , Stephen G. Walker

Meta-Learning has gained increasing attention in the machine learning and artificial intelligence communities. In this paper, we introduce and study an adaptive submodular meta-learning problem. The input of our problem is a set of items,…

Machine Learning · Computer Science 2021-03-26 Shaojie Tang , Jing Yuan

We consider online prediction of a latent dynamic spatiotemporal process and estimation of the associated model parameters based on noisy data. The problem is motivated by the analysis of spatial data arriving in real-time and the current…

Computation · Statistics 2017-08-14 Evangelos Evangelou , Vasileios Maroulas

To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks. However, the inconsistent task distribution and heterogeneity is hard to be handled through a global sharing model…

Machine Learning · Computer Science 2022-06-22 Geng Li , Boyuan Ren , Hongzhi Wang

Many sequential decision-making problems that are currently automated, such as those in manufacturing or recommender systems, operate in an environment where there is either little uncertainty, or zero risk of catastrophe. As companies and…

Machine Learning · Computer Science 2023-04-04 Marc Rigter

We explore the problem of learning under selective labels in the context of algorithm-assisted decision making. Selective labels is a pervasive selection bias problem that arises when historical decision making blinds us to the true outcome…

Machine Learning · Computer Science 2018-07-06 Maria De-Arteaga , Artur Dubrawski , Alexandra Chouldechova

A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural…

Machine Learning · Computer Science 2019-11-01 Rahaf Aljundi , Min Lin , Baptiste Goujaud , Yoshua Bengio