English
Related papers

Related papers: Off-policy Evaluation with Deeply-abstracted State…

200 papers

The world currently offers an abundance of data in multiple domains, from which we can learn reinforcement learning (RL) policies without further interaction with the environment. RL agents learning offline from such data is possible but…

Machine Learning · Computer Science 2022-12-19 Hager Radi , Josiah P. Hanna , Peter Stone , Matthew E. Taylor

This paper demonstrates the successful application of Off-Policy Evaluation (OPE) to accelerate recommender system development and optimization at Adyen, a global leader in financial payment processing. Facing the limitations of traditional…

Machine Learning · Computer Science 2025-01-22 Alex Egg

In real-world recommender systems and search engines, optimizing ranking decisions to present a ranked list of relevant items is critical. Off-policy evaluation (OPE) for ranking policies is thus gaining a growing interest because it…

Machine Learning · Statistics 2022-02-04 Haruka Kiyohara , Yuta Saito , Tatsuya Matsuhiro , Yusuke Narita , Nobuyuki Shimizu , Yasuo Yamamoto

Importance sampling is a central idea underlying off-policy prediction in reinforcement learning. It provides a strategy for re-weighting samples from a distribution to obtain unbiased estimates under another distribution. However,…

Machine Learning · Computer Science 2023-06-28 Kristopher De Asis , Eric Graves , Richard S. Sutton

In many real-world decision problems there is partially observed, hidden or latent information that remains fixed throughout an interaction. Such decision problems can be modeled as Latent Markov Decision Processes (LMDPs), where a latent…

Machine Learning · Computer Science 2024-06-27 Jeongyeol Kwon , Shie Mannor , Constantine Caramanis , Yonathan Efroni

We devise and analyze algorithms for the empirical policy evaluation problem in reinforcement learning. Our algorithms explore backward from high-cost states to find high-value ones, in contrast to forward approaches that work forward from…

Machine Learning · Computer Science 2022-03-02 Daniel Vial , Vijay Subramanian

This work introduces a new abstraction technique for reducing the state space of large, discrete-time labelled Markov chains. The abstraction leverages the semantics of interval Markov decision processes and the existing notion of…

Systems and Control · Computer Science 2019-03-08 Y. Zacchia Lun , J. Wheatley , A. D'Innocenzo , A. Abate

The need to model a Markov renewal on-off process with multiple off-states arise in many applications such as economics, physics, and engineering. Characterization of the occupation time of one specific off-state marginally or two…

Probability · Mathematics 2019-10-01 Chaoran Hu , Vladimir Pozdnyakov , Jun Yan

Abstraction is one of the most important strategies for dealing with the state space explosion problem in model checking. In the abstract model, although the state space is largely reduced, however, a counterexample found in such a model…

Logic in Computer Science · Computer Science 2010-07-27 Cong Tian , Zhenhua Duan

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

Partially observable Markov decision processes (POMDPs) are a general mathematical model for sequential decision-making in stochastic environments under state uncertainty. POMDPs are often solved \textit{online}, which enables the algorithm…

Artificial Intelligence · Computer Science 2025-03-26 Yunuo Zhang , Baiting Luo , Ayan Mukhopadhyay , Abhishek Dubey

Predictive models are fundamental to engineering reliable software systems. However, designing conservative, computable approximations for the behavior of programs (static analyses) remains a difficult and error-prone process for modern…

Programming Languages · Computer Science 2011-05-10 David Van Horn , Matthew Might

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

Markov Decision Processes (MDPs) are mathematical models of sequential decision-making under uncertainty that have found applications in healthcare, manufacturing, logistics, and others. In these models, a decision-maker observes the state…

Optimization and Control · Mathematics 2024-05-22 Madeleine Pollack , Lauren N. Steimle

We study off-policy evaluation (OPE) of contextual bandit policies for large discrete action spaces where conventional importance-weighting approaches suffer from excessive variance. To circumvent this variance issue, we propose a new…

Machine Learning · Statistics 2023-06-12 Yuta Saito , Qingyang Ren , Thorsten Joachims

We study a novel setting in Online Markov Decision Processes (OMDPs) where the loss function is chosen by a non-oblivious strategic adversary who follows a no-external regret algorithm. In this setting, we first demonstrate that MDP-Expert,…

Machine Learning · Computer Science 2023-01-31 Le Cong Dinh , David Henry Mguni , Long Tran-Thanh , Jun Wang , Yaodong Yang

POMDPs are useful models for systems where the true underlying state is not known completely to an outside observer; the outside observer incompletely knows the true state of the system, and observes a noisy version of the true system…

Machine Learning · Computer Science 2021-09-01 Caleb M. Bowyer

Motivated by the recent discovery of a statistical and computational reduction from contextual bandits to offline regression (Simchi-Levi and Xu, 2021), we address the general (stochastic) Contextual Markov Decision Process (CMDP) problem…

Machine Learning · Computer Science 2024-05-29 Jian Qian , Haichen Hu , David Simchi-Levi

Off-policy evaluation (OPE) is a fundamental task in reinforcement learning (RL). In the classic setting of linear OPE, finite-sample guarantees often take the form $$ \textrm{Evaluation error} \le \textrm{poly}(C^\pi, d,…

Machine Learning · Computer Science 2026-01-28 Philip Amortila , Audrey Huang , Akshay Krishnamurthy , Nan Jiang

We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, collected by other agents, we seek to obtain a (tight) lower bound on a policy's performance. This is crucial when…

Machine Learning · Computer Science 2023-05-29 Jonas Rothfuss , Bhavya Sukhija , Tobias Birchler , Parnian Kassraie , Andreas Krause