English
Related papers

Related papers: Low Variance Off-policy Evaluation with State-base…

200 papers

We present a new method for estimating the expected return of a POMDP from experience. The method does not assume any knowledge of the POMDP and allows the experience to be gathered from an arbitrary sequence of policies. The return is…

Artificial Intelligence · Computer Science 2013-01-14 Christian R. Shelton

Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency.…

Machine Learning · Computer Science 2018-11-16 Sergey Pankov

A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In…

Machine Learning · Computer Science 2018-04-25 Weichao Li , Fuxian Huang , Xi Li , Gang Pan , Fei Wu

Off-policy Actor-Critic algorithms have demonstrated phenomenal experimental performance but still require better explanations. To this end, we show its policy evaluation error on the distribution of transitions decomposes into: a Bellman…

Machine Learning · Computer Science 2021-10-07 Ting-Han Fan , Peter J. Ramadge

We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another policy(ies). In particular, we focus on the doubly robust (DR)…

Artificial Intelligence · Computer Science 2018-05-25 Mehrdad Farajtabar , Yinlam Chow , Mohammad Ghavamzadeh

Importance sampling is widely used in machine learning and statistics, but its power is limited by the restriction of using simple proposals for which the importance weights can be tractably calculated. We address this problem by studying…

Machine Learning · Statistics 2016-10-18 Qiang Liu , Jason D. Lee

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning…

Stateful policies play an important role in reinforcement learning, such as handling partially observable environments, enhancing robustness, or imposing an inductive bias directly into the policy structure. The conventional method for…

Machine Learning · Computer Science 2023-11-08 Firas Al-Hafez , Guoping Zhao , Jan Peters , Davide Tateo

Recent work on policy learning from observational data has highlighted the importance of efficient policy evaluation and has proposed reductions to weighted (cost-sensitive) classification. But, efficient policy evaluation need not yield…

Machine Learning · Computer Science 2020-02-13 Andrew Bennett , Nathan Kallus

Off-policy learning and evaluation leverage logged bandit feedback datasets, which contain context, action, propensity score, and feedback for each data point. These scenarios face significant challenges due to high variance and poor…

Machine Learning · Computer Science 2025-06-10 Armin Behnamnia , Gholamali Aminian , Alireza Aghaei , Chengchun Shi , Vincent Y. F. Tan , Hamid R. Rabiee

State-space models have been used in many applications, including econometrics, engineering, medical research, etc. The maximum likelihood estimation (MLE) of the static parameter of general state-space models is not straightforward because…

Methodology · Statistics 2025-02-04 Yuxiong Gao , Wentao Li , Rong Chen

Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper, we illustrate this in a continuous control setting where state of the art methods perform poorly…

Machine Learning · Computer Science 2019-05-24 Pierre Thodoroff , Nishanth Anand , Lucas Caccia , Doina Precup , Joelle Pineau

Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently explored competitive alternative is to learn a single value…

Machine Learning · Computer Science 2022-07-05 Francesco Faccio , Aditya Ramesh , Vincent Herrmann , Jean Harb , Jürgen Schmidhuber

Off-policy evaluation is critical in a number of applications where new policies need to be evaluated offline before online deployment. Most existing methods focus on the expected return, define the target parameter through averaging and…

Machine Learning · Statistics 2023-02-10 Yingying Zhang , Chengchun Shi , Shikai Luo

Offline reinforcement learning aims to utilize datasets of previously gathered environment-action interaction records to learn a policy without access to the real environment. Recent work has shown that offline reinforcement learning can be…

Machine Learning · Computer Science 2023-08-30 Hanhan Zhou , Tian Lan , Vaneet Aggarwal

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, but counteracting off-policy bias without exacerbating variance is challenging. Classically, off-policy bias is corrected in a per-decision…

Machine Learning · Computer Science 2025-12-23 Brett Daley , Martha White , Christopher Amato , Marlos C. Machado

To unbiasedly evaluate multiple target policies, the dominant approach among RL practitioners is to run and evaluate each target policy separately. However, this evaluation method is far from efficient because samples are not shared across…

Machine Learning · Computer Science 2024-12-30 Shuze Daniel Liu , Claire Chen , Shangtong Zhang

Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed in the past. Not all samples carry the same amount of significance and simply assigning equal…

Machine Learning · Computer Science 2023-11-02 Shivakanth Sujit , Somjit Nath , Pedro H. M. Braga , Samira Ebrahimi Kahou

In this paper we study simulation-based methods for estimating gradients in stochastic networks. We derive a new method of calculating weak derivative estimator using importance sampling transform, and our method has less computational cost…

Methodology · Statistics 2023-03-28 Cheng Jie , Michael C Fu

In offline reinforcement learning, a policy learns to maximize cumulative rewards with a fixed collection of data. Towards conservative strategy, current methods choose to regularize the behavior policy or learn a lower bound of the value…

Machine Learning · Computer Science 2021-03-02 Hongchang Zhang , Jianzhun Shao , Yuhang Jiang , Shuncheng He , Xiangyang Ji