English
Related papers

Related papers: A Relative Ignorability Framework for Decision-Rel…

200 papers

We study the problem of ignorability in likelihood-based inference from incomplete categorical data. Two versions of the coarsened at random assumption (car) are distinguished, their compatibility with the parameter distinctness assumption…

Statistics Theory · Mathematics 2007-06-13 Manfred Jaeger

Robustness has been extensively studied in reinforcement learning (RL) to handle various forms of uncertainty such as random perturbations, rare events, and malicious attacks. In this work, we consider one critical type of robustness…

Machine Learning · Computer Science 2023-10-27 Wenhao Ding , Laixi Shi , Yuejie Chi , Ding Zhao

As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs. By encoding a series of cause-effect relations between events,…

Machine Learning · Computer Science 2020-01-16 Yuhao Wang , Vlado Menkovski , Hao Wang , Xin Du , Mykola Pechenizkiy

The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning. In this paper, we propose a novel Forward-Backward Learning procedure to test MA in sequential decision making. The proposed test does not assume…

Machine Learning · Statistics 2020-02-06 Chengchun Shi , Runzhe Wan , Rui Song , Wenbin Lu , Ling Leng

This paper proposes a new sequential model learning architecture to solve partially observable Markov decision problems. Rather than compressing sequential information at every timestep as in conventional recurrent neural network-based…

Machine Learning · Computer Science 2021-12-13 Giseung Park , Sungho Choi , Youngchul Sung

This paper concerns outcome missingness in principal stratification analysis. We revisit a common assumption known as latent ignorability or latent missing-at-random (LMAR), often considered a relaxation of missing-at-random (MAR). LMAR…

Methodology · Statistics 2024-07-22 Trang Quynh Nguyen

A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the observations generated by the Markov Decision Process…

Machine Learning · Computer Science 2020-01-01 Xingyou Song , Yiding Jiang , Stephen Tu , Yilun Du , Behnam Neyshabur

Due to recent breakthroughs, reinforcement learning (RL) has demonstrated impressive performance in challenging sequential decision-making problems. However, an open question is how to make RL cope with partial observability which is…

Machine Learning · Computer Science 2021-04-23 Stephan Weigand , Pascal Klink , Jan Peters , Joni Pajarinen

We study the problem of inverse reinforcement learning (IRL), where the learning agent recovers a reward function using expert demonstrations. Most of the existing IRL techniques make the often unrealistic assumption that the agent has…

Machine Learning · Computer Science 2021-12-20 Franck Djeumou , Murat Cubuktepe , Craig Lennon , Ufuk Topcu

We introduce the Markov missing graph (MMG), a novel framework that imputes missing data based on undirected graphs. MMG leverages conditional independence relationships to locally decompose the imputation model. To establish the…

Methodology · Statistics 2025-09-04 Yanjiao Yang , Yen-Chi Chen

Reinforcementlearning(RL)folkloresuggeststhathistory-basedfunctionapproximationmethods,suchas recurrent neural nets or history-based state abstraction, perform better than their memory-less counterparts, due to the fact that function…

Machine Learning · Computer Science 2022-11-08 Gandharv Patil , Aditya Mahajan , Doina Precup

We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems. While risk-sensitive formulations for Markov decision processes studied so far focus on the distribution of the…

Machine Learning · Computer Science 2020-09-16 Nelson Vadori , Sumitra Ganesh , Prashant Reddy , Manuela Veloso

The equivalence of realizable and agnostic learnability is a fundamental phenomenon in learning theory. With variants ranging from classical settings like PAC learning and regression to recent trends such as adversarially robust learning,…

Machine Learning · Computer Science 2024-08-07 Max Hopkins , Daniel M. Kane , Shachar Lovett , Gaurav Mahajan

In many application settings, the data have missing entries which make analysis challenging. An abundant literature addresses missing values in an inferential framework: estimating parameters and their variance from incomplete tables. Here,…

Machine Learning · Statistics 2024-03-22 Julie Josse , Jacob M. Chen , Nicolas Prost , Erwan Scornet , Gaël Varoquaux

Real-world sequential decision making problems commonly involve partial observability, which requires the agent to maintain a memory of history in order to infer the latent states, plan and make good decisions. Coping with partial…

Machine Learning · Computer Science 2022-02-09 Yonathan Efroni , Chi Jin , Akshay Krishnamurthy , Sobhan Miryoosefi

This paper introduces an algorithm for discovering implicit and delayed causal relations between events observed by a robot at arbitrary times, with the objective of improving data-efficiency and interpretability of model-based…

Machine Learning · Computer Science 2020-08-05 Junchi Liang , Abdeslam Boularias

Inverse reinforcement learning (IRL) aims to explain observed strategic behavior by fitting reinforcement learning models to behavioral data. However, traditional IRL methods are only applicable when the observations are in the form of…

Machine Learning · Computer Science 2018-06-26 Antti Kangasrääsiö , Samuel Kaski

Reinforcement learning (RL) methods frequently assume that each new observation completely reflects the environment's state, thereby guaranteeing Markovian (one-step) transitions. In practice, partial observability or sensor/actuator noise…

Machine Learning · Computer Science 2025-06-03 Naveen Mysore

Noncompliance and missing data often occur in randomized trials, which complicate the inference of causal effects. When both noncompliance and missing data are present, previous papers proposed moment and maximum likelihood estimators for…

Methodology · Statistics 2014-09-04 Hua Chen , Peng Ding , Zhi Geng , Xiao-Hua Zhou

It is often said that the fundamental problem of causal inference is a missing data problem -- the comparison of responses to two hypothetical treatment assignments is made difficult because for every experimental unit only one potential…

Methodology · Statistics 2024-11-21 Razieh Nabi , Rohit Bhattacharya , Ilya Shpitser , James M. Robins