English
Related papers

Related papers: Efficient and Sharp Off-Policy Evaluation in Robus…

200 papers

Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and…

Machine Learning · Computer Science 2023-03-14 Esther Derman , Yevgeniy Men , Matthieu Geist , Shie Mannor

Algorithms developed under stationary Markov Decision Processes (MDPs) often face challenges in non-stationary environments, and infinite-horizon formulations may not directly apply to finite-horizon tasks. To address these limitations, we…

Machine Learning · Computer Science 2025-12-03 Zhizuo Chen , Theodore T. Allen

Controllers for autonomous systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modelled as process noise, and common assumptions are that the underlying distributions are…

Systems and Control · Electrical Eng. & Systems 2022-12-08 Thom S. Badings , Alessandro Abate , Nils Jansen , David Parker , Hasan A. Poonawala , Marielle Stoelinga

We study policy evaluation of offline contextual bandits subject to unobserved confounders. Sensitivity analysis methods are commonly used to estimate the policy value under the worst-case confounding over a given uncertainty set. However,…

Machine Learning · Statistics 2023-09-25 Kei Ishikawa , Niao He

Robust Markov Decision Processes (MDPs) are a powerful framework for modeling sequential decision-making problems with model uncertainty. This paper proposes the first first-order framework for solving robust MDPs. Our algorithm interleaves…

Optimization and Control · Mathematics 2021-01-18 Julien Grand-Clément , Christian Kroer

In this paper, we propose a policy gradient method for confounded partially observable Markov decision processes (POMDPs) with continuous state and observation spaces in the offline setting. We first establish a novel identification result…

Machine Learning · Statistics 2023-12-04 Mao Hong , Zhengling Qi , Yanxun Xu

Policy robustness in Reinforcement Learning may not be desirable at any cost: the alterations caused by robustness requirements from otherwise optimal policies should be explainable, quantifiable and formally verifiable. In this work we…

Machine Learning · Computer Science 2023-12-12 Daniel Jarne Ornia , Licio Romao , Lewis Hammond , Manuel Mazo , Alessandro Abate

Risk-sensitive planning aims to identify policies maximizing some tail-focused metrics in Markov Decision Processes (MDPs). Such an optimization task can be very costly for the most widely used and interpretable metrics such as threshold…

Machine Learning · Statistics 2025-07-09 Alexandre Marthe , Samuel Bounan , Aurélien Garivier , Claire Vernade

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

This paper develops a robust and efficient method for policy learning from observational data in the presence of unobserved confounding, complementing existing instrumental variable (IV) based approaches. We employ the marginal sensitivity…

Econometrics · Economics 2025-07-29 Zequn Jin , Gaoqian Xu , Xi Zheng , Yahong Zhou

In this paper, we show how a simulated Markov decision process (MDP) built by the so-called \emph{baseline} policies, can be used to compute a different policy, namely the \emph{simulated optimal} policy, for which the performance of this…

Optimization and Control · Mathematics 2014-10-13 Yinlam Chow , Mohammad Ghavamzadeh

An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the reward function are unknown, a learning agent must discover an…

Machine Learning · Computer Science 2019-07-19 Boris Belousov , Jan Peters

This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation…

Machine Learning · Statistics 2024-05-03 Gen Li , Weichen Wu , Yuejie Chi , Cong Ma , Alessandro Rinaldo , Yuting Wei

In this paper, we consider risk-sensitive Markov Decision Processes (MDPs) with Borel state and action spaces and unbounded cost under both finite and infinite planning horizons. Our optimality criterion is based on the recursive…

Optimization and Control · Mathematics 2025-10-16 Nicole Bäuerle , Alexander Glauner

For many Markov chains of practical interest, the invariant distribution is extremely sensitive to perturbations of some entries of the transition matrix, but insensitive to others; we give an example of such a chain, motivated by a problem…

Numerical Analysis · Mathematics 2015-10-12 Erik Thiede , Brian Van Koten , Jonathan Weare

We study Off-Policy Evaluation (OPE) in contextual bandit settings with large action spaces. The benchmark estimators suffer from severe bias and variance tradeoffs. Parametric approaches suffer from bias due to difficulty specifying the…

Machine Learning · Statistics 2023-12-15 Tatsuhiro Shimizu , Laura Forastiere

We present a framework to address a class of sequential decision making problems. Our framework features learning the optimal control policy with robustness to noisy data, determining the unknown state and action parameters, and performing…

Machine Learning · Computer Science 2022-01-20 Amber Srivastava , Srinivasa M Salapaka

Optimal decision-making presents a significant challenge for autonomous systems operating in uncertain, stochastic and time-varying environments. Environmental variability over time can significantly impact the system's optimal decision…

Robotics · Computer Science 2024-03-11 Gokul Puthumanaillam , Xiangyu Liu , Negar Mehr , Melkior Ornik

We study variance-dependent regret bounds for Markov decision processes (MDPs). Algorithms with variance-dependent regret guarantees can automatically exploit environments with low variance (e.g., enjoying constant regret on deterministic…

Machine Learning · Computer Science 2023-05-23 Runlong Zhou , Zihan Zhang , Simon S. Du

This paper investigates a series of optimization problems for one-counter Markov decision processes (MDPs) and integer-weighted MDPs with finite state space. Specifically, it considers problems addressing termination probabilities and…

Logic in Computer Science · Computer Science 2024-08-07 Jakob Piribauer , Christel Baier