中文
相关论文

相关论文: Unified Off-Policy Learning to Rank: a Reinforceme…

200 篇论文

Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) generative modeling, i.e., approximating a policy using fixed…

机器学习 · 计算机科学 2021-06-23 Hua Wei , Deheng Ye , Zhao Liu , Hao Wu , Bo Yuan , Qiang Fu , Wei Yang , Zhenhui Li

Offline reinforcement learning (RL) aims to find an optimal policy for Markov decision processes (MDPs) using a pre-collected dataset. In this work, we revisit the linear programming (LP) reformulation of Markov decision processes for…

机器学习 · 计算机科学 2024-12-11 Asuman Ozdaglar , Sarath Pattathil , Jiawei Zhang , Kaiqing Zhang

Offline (or batch) reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offline dataset, two main categories of methods are used:…

机器学习 · 计算机科学 2023-07-04 Paria Rashidinejad , Banghua Zhu , Cong Ma , Jiantao Jiao , Stuart Russell

In the framework of Markov Decision Processes, off-policy learning, that is the problem of learning a linear approximation of the value function of some fixed policy from one trajectory possibly generated by some other policy. We briefly…

人工智能 · 计算机科学 2013-04-16 Matthieu Geist , Bruno Scherrer

Offline Reinforcement Learning (RL) is structured to derive policies from static trajectory data without requiring real-time environment interactions. Recent studies have shown the feasibility of framing offline RL as a sequence modeling…

机器学习 · 计算机科学 2023-09-01 Abdelghani Ghanem , Philippe Ciblat , Mounir Ghogho

Reactive synthesis algorithms allow automatic construction of policies to control an environment modeled as a Markov Decision Process (MDP) that are optimal with respect to high-level temporal logic specifications. However, they assume that…

形式语言与自动机理论 · 计算机科学 2022-05-31 Rajeev Alur , Suguman Bansal , Osbert Bastani , Kishor Jothimurugan

Learning-to-rank (LTR) is a class of supervised learning techniques that apply to ranking problems dealing with a large number of features. The popularity and widespread application of LTR models in prioritizing information in a variety of…

机器学习 · 计算机科学 2020-05-19 Jaspreet Singh , Zhenye Wang , Megha Khosla , Avishek Anand

Offline-to-online reinforcement learning (RL) leverages both pre-trained offline policies and online policies trained for downstream tasks, aiming to improve data efficiency and accelerate performance enhancement. An existing approach,…

机器学习 · 计算机科学 2024-11-01 JaeYoon Kim , Junyu Xuan , Christy Liang , Farookh Hussain

Ordinal regression and ranking are challenging due to inherent ordinal dependencies that conventional methods struggle to model. We propose Ranking-Aware Reinforcement Learning (RARL), a novel RL framework that explicitly learns these…

机器学习 · 计算机科学 2026-01-29 Aiming Hao , Chen Zhu , Jiashu Zhu , Jiahong Wu , Xiangxiang Chu

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be…

机器学习 · 计算机科学 2022-10-25 Rui Yang , Chenjia Bai , Xiaoteng Ma , Zhaoran Wang , Chongjie Zhang , Lei Han

This study presents a novel approach to addressing offline reinforcement learning (RL) problems by reframing them as regression tasks that can be effectively solved using Decision Trees. Mainly, we introduce two distinct frameworks:…

机器学习 · 计算机科学 2024-10-16 Prajwal Koirala , Cody Fleming

Offline reinforcement learning (RL) is a powerful approach for data-driven decision-making and control. Compared to model-free methods, offline model-based reinforcement learning (MBRL) explicitly learns world models from a static dataset…

机器学习 · 计算机科学 2026-01-28 Jiayu Chen , Le Xu , Wentse Chen , Jeff Schneider

Reinforcement learning (RL) is a powerful machine learning technique that enables an intelligent agent to learn an optimal policy that maximizes the cumulative rewards in sequential decision making. Most of methods in the existing…

机器学习 · 统计学 2023-01-06 Chengchun Shi , Zhengling Qi , Jianing Wang , Fan Zhou

Offline reinforcement learning (RL purely from logged data) is an important avenue for deploying RL techniques in real-world scenarios. However, existing hyperparameter selection methods for offline RL break the offline assumption by…

With the aim of improving performance in Markov Decision Problem in an Off-Policy setting, we suggest taking inspiration from what is done in Offline Reinforcement Learning (RL). In Offline RL, it is a common practice during policy learning…

人工智能 · 计算机科学 2024-10-29 Jérôme Arjonilla , Abdallah Saffidine , Tristan Cazenave

Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. We consider for the first time the semiparametric…

机器学习 · 计算机科学 2020-06-08 Nathan Kallus , Masatoshi Uehara

In Online Learning to Rank (OLTR) the aim is to find an optimal ranking model by interacting with users. When learning from user behavior, systems must interact with users while simultaneously learning from those interactions. Unlike other…

信息检索 · 计算机科学 2017-11-28 Harrie Oosterhuis , Maarten de Rijke

With the advent of large datasets, offline reinforcement learning (RL) is a promising framework for learning good decision-making policies without the need to interact with the real environment. However, offline RL requires the dataset to…

机器学习 · 计算机科学 2023-03-27 Yicheng Luo , Zhengyao Jiang , Samuel Cohen , Edward Grefenstette , Marc Peter Deisenroth

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…

机器学习 · 计算机科学 2021-02-12 Mengjiao Yang , Ofir Nachum

Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…

机器学习 · 计算机科学 2021-09-24 Aviral Kumar , Anikait Singh , Stephen Tian , Chelsea Finn , Sergey Levine