English
Related papers

Related papers: Kernel Metric Learning for In-Sample Off-Policy Ev…

200 papers

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

Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline datasets, the principle…

Machine Learning · Computer Science 2022-06-14 Laixi Shi , Gen Li , Yuting Wei , Yuxin Chen , Yuejie Chi

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues…

Machine Learning · Computer Science 2020-09-15 Daoming Lyu , Qi Qi , Mohammad Ghavamzadeh , Hengshuai Yao , Tianbao Yang , Bo Liu

Real-world decision-making tasks are usually partially observable Markov decision processes (POMDPs), where the state is not fully observable. Recent progress has demonstrated that recurrent reinforcement learning (RL), which consists of a…

Machine Learning · Computer Science 2024-05-27 Fan-Ming Luo , Zuolin Tu , Zefang Huang , Yang Yu

Recent Offline Reinforcement Learning methods have succeeded in learning high-performance policies from fixed datasets of experience. A particularly effective approach learns to first identify and then mimic optimal decision-making…

Machine Learning · Computer Science 2023-12-12 Jake Grigsby , Yanjun Qi

Training practical agents usually involve offline and online reinforcement learning (RL) to balance the policy's performance and interaction costs. In particular, online fine-tuning has become a commonly used method to correct the erroneous…

Machine Learning · Computer Science 2023-06-07 Qisen Yang , Shenzhi Wang , Matthieu Gaetan Lin , Shiji Song , Gao Huang

The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online…

Machine Learning · Computer Science 2024-08-15 Shashank Gupta , Olivier Jeunen , Harrie Oosterhuis , Maarten de Rijke

Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present…

Machine Learning · Computer Science 2020-03-06 Arjun Sondhi , David Arbour , Drew Dimmery

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Machine Learning · Computer Science 2024-05-31 Zeyu Fang , Tian Lan

In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while…

Machine Learning · Computer Science 2021-11-02 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

We introduce an offline reinforcement learning (RL) algorithm that explicitly clones a behavior policy to constrain value learning. In offline RL, it is often important to prevent a policy from selecting unobserved actions, since the…

Machine Learning · Computer Science 2022-06-03 Wonjoon Goo , Scott Niekum

Developing theoretical guarantees on the sample complexity of offline RL methods is an important step towards making data-hungry RL algorithms practically viable. Currently, most results hinge on unrealistic assumptions about the data…

Machine Learning · Computer Science 2024-05-02 Sunil Madhow , Dan Qiao , Ming Yin , Yu-Xiang Wang

Model-free reinforcement learning (RL) methods are succeeding in a growing number of tasks, aided by recent advances in deep learning. However, they tend to suffer from high sample complexity, which hinders their use in real-world domains.…

Machine Learning · Computer Science 2018-10-08 Thanard Kurutach , Ignasi Clavera , Yan Duan , Aviv Tamar , Pieter Abbeel

This paper discusses an Enhanced Model-Agnostic Meta-Learning (E-MAML) algorithm that generates fast convergence of the policy function from a small number of training examples when applied to new learning tasks. Built on top of…

Machine Learning · Computer Science 2020-12-14 Ibrahim Ahmed , Marcos Quinones-Grueiro , Gautam Biswas

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in two settings: learning interactively in the environment (online RL), or learning from an offline dataset (offline RL). However, existing algorithms…

Machine Learning · Computer Science 2022-02-14 Tengyang Xie , Nan Jiang , Huan Wang , Caiming Xiong , Yu Bai

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

Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is especially observed in many widely popular policy gradient…

Machine Learning · Computer Science 2020-08-04 Samuele Tosatto , Joao Carvalho , Hany Abdulsamad , Jan Peters

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

Contextual bandit algorithms are ubiquitous tools for active sequential experimentation in healthcare and the tech industry. They involve online learning algorithms that adaptively learn policies over time to map observed contexts $X_t$ to…

Methodology · Statistics 2024-08-19 Ian Waudby-Smith , Lili Wu , Aaditya Ramdas , Nikos Karampatziakis , Paul Mineiro