paper-with-me

Papers

IMO$^3$: Interactive Multi-Objective Off-Policy Optimization

2022-01-24 · Nan Wang, Hongning Wang, Maryam Karimzadehgan, Branislav Kveton, Craig Boutilier

Most real-world optimization problems have multiple objectives. A system designer needs to find a policy that trades off these objectives to reach a desired operating point. This problem has been studied extensively in the setting of known objective functions. We consider a more practical but challenging setting of unknown objective functions. In industry, this problem is mostly approached with online A/B testing, which is often costly and inefficient. As an alternative, we propose interactive multi-objective off-policy optimization (IMO$^3$). The key idea in our approach is to interact with a system designer using policies evaluated in an off-policy fashion to uncover which policy maximizes her unknown utility function. We theoretically show that IMO$^3$ identifies a near-optimal policy with high probability, depending on the amount of feedback from the designer and training data for off-policy estimation. We demonstrate its effectiveness empirically on multiple multi-objective optimization problems.

📄 PDF Abstract BibTeX arXiv:2201.09798

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Optimizing Interactive Systems via Data-Driven Objectives

2020-06-19 · Ziming Li, Julia Kiseleva, Alekh Agarwal, Maarten de Rijke 외

Effective optimization is essential for real-world interactive systems to provide a satisfactory user experience in response to changing user behavior. However, it is often challenging to find an objective to optimize fo…

Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning

2024-01-04 · Ke Li, Han Guo

Multi-objective reinforcement learning (MORL) aims to find a set of high-performing and diverse policies that address trade-offs between multiple conflicting objectives. However, in practice, decision makers (DMs) often …

Decision MakingManagementMulti-Objective Reinforcement Learning

Multi-Objective Autonomous Braking System using Naturalistic Dataset

2019-04-15 · Rafael Vasquez, Bilal Farooq

A deep reinforcement learning based multi-objective autonomous braking system is presented. The design of the system is formulated in a continuous action space and seeks to maximize both pedestrian safety and perception …

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Learning Data-Driven Objectives to Optimize Interactive Systems

2018-02-17 · Ziming Li, Julia Kiseleva, Alekh Agarwal, Maarten de Rijke

Effective optimization is essential for interactive systems to provide a satisfactory user experience. However, it is often challenging to find an objective to optimize for. Generally, such objectives are manually crafte…

SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning

2026-08-20 · Dayang Liang, Lang Feng, Bo An, Yunlong Liu arxiv

Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy advantages from multiple rollouts, avoiding the …

Reinforcement Learning