English
Related papers

Related papers: Projected State-action Balancing Weights for Offli…

200 papers

We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of…

When using reinforcement learning (RL) algorithms to evaluate a policy it is common, given a large state space, to introduce some form of approximation architecture for the value function (VF). The exact form of this architecture can have a…

Artificial Intelligence · Computer Science 2017-03-06 Edward W. Barker , Charl J. Ras

We study reinforcement learning for partially observed Markov decision processes (POMDPs) with infinite observation and state spaces, which remains less investigated theoretically. To this end, we make the first attempt at bridging partial…

Machine Learning · Computer Science 2024-04-02 Qi Cai , Zhuoran Yang , Zhaoran Wang

This work studies the statistical limits of uniform convergence for offline policy evaluation (OPE) problems with model-based methods (for episodic MDP) and provides a unified framework towards optimal learning for several well-motivated…

Machine Learning · Computer Science 2021-06-25 Ming Yin , Yu-Xiang Wang

We study offline multi-agent reinforcement learning (RL) in Markov games, where the goal is to learn an approximate equilibrium -- such as Nash equilibrium and (Coarse) Correlated Equilibrium -- from an offline dataset pre-collected from…

Machine Learning · Computer Science 2023-02-07 Yuheng Zhang , Yu Bai , Nan Jiang

In systems governed by nonlinear partial differential equations such as fluid flows, the design of state estimators such as Kalman filters relies on a reduced-order model (ROM) that projects the original high-dimensional dynamics onto a…

Machine Learning · Computer Science 2024-04-05 Saviz Mowlavi , Mouhacine Benosman

Existing theoretical studies on offline reinforcement learning (RL) mostly consider a dataset sampled directly from the target task. In practice, however, data often come from several heterogeneous but related sources. Motivated by this…

Machine Learning · Statistics 2023-06-16 Chengshuai Shi , Wei Xiong , Cong Shen , Jing Yang

Off-Policy Evaluation (OPE) is employed to assess the potential impact of a hypothetical policy using logged contextual bandit feedback, which is crucial in areas such as personalized medicine and recommender systems, where online…

Machine Learning · Computer Science 2025-07-10 Yuqi Bai , Ziyu Zhao , Chenxin Lyu , Minqin Zhu , Kun Kuang

Reinforcement learning (RL) -- finding the optimal behaviour (also referred to as policy) maximizing the collected long-term cumulative reward -- is among the most influential approaches in machine learning with a large number of successful…

Machine Learning · Statistics 2025-02-28 Tao Ma , Xuzhi Yang , Zoltan Szabo

Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances in OPL primarily optimize OPE estimators with improved statistical properties, assuming that…

Machine Learning · Statistics 2025-09-04 Imad Aouali , Otmane Sakhi

We study off-policy evaluation (OPE) from multiple logging policies, each generating a dataset of fixed size, i.e., stratified sampling. Previous work noted that in this setting the ordering of the variances of different importance sampling…

Machine Learning · Computer Science 2020-10-22 Nathan Kallus , Yuta Saito , Masatoshi Uehara

We introduce a novel doubly-robust (DR) off-policy evaluation (OPE) estimator for Markov decision processes, DRUnknown, designed for situations where both the logging policy and the value function are unknown. The proposed estimator…

Machine Learning · Statistics 2024-04-03 Kyungbok Lee , Myunghee Cho Paik

Constraint-based offline reinforcement learning (RL) involves policy constraints or imposing penalties on the value function to mitigate overestimation errors caused by distributional shift. This paper focuses on a limitation in existing…

Machine Learning · Computer Science 2024-10-25 Junghyuk Yeom , Yonghyeon Jo , Jungmo Kim , Sanghyeon Lee , Seungyul Han

Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong…

Machine Learning · Computer Science 2023-05-23 Germano Gabbianelli , Gergely Neu , Nneka Okolo , Matteo Papini

Goal-oriented Reinforcement Learning, where the agent needs to reach the goal state while simultaneously minimizing the cost, has received significant attention in real-world applications. Its theoretical formulation, stochastic shortest…

Machine Learning · Computer Science 2022-06-13 Ming Yin , Wenjing Chen , Mengdi Wang , Yu-Xiang Wang

Offline reinforcement learning (RL) is a challenging setting where existing off-policy actor-critic methods perform poorly due to the overestimation of out-of-distribution state-action pairs. Thus, various additional augmentations are…

Machine Learning · Computer Science 2023-02-23 Zifeng Zhuang , Kun Lei , Jinxin Liu , Donglin Wang , Yilang Guo

Off-policy evaluation (OPE) is the method that attempts to estimate the performance of decision making policies using historical data generated by different policies without conducting costly online A/B tests. Accurate OPE is essential in…

Artificial Intelligence · Computer Science 2021-09-20 Yuta Saito , Takuma Udagawa , Kei Tateno

Counterfactual estimators are critical for learning and refining policies using logged data, a process known as Off-Policy Evaluation (OPE). OPE allows researchers to assess new policies without costly experiments, speeding up the…

Artificial Intelligence · Computer Science 2025-01-10 Ritam Guha , Nilavra Pathak

Learning high-quality $Q$-value functions plays a key role in the success of many modern off-policy deep reinforcement learning (RL) algorithms. Previous works primarily focus on addressing the value overestimation issue, an outcome of…

Machine Learning · Computer Science 2024-05-14 Tianying Ji , Yu Luo , Fuchun Sun , Xianyuan Zhan , Jianwei Zhang , Huazhe Xu

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Samin Yeasar Arnob , Doina Precup