Strategyproof reinforcement learning for online resource allocation

Sebastian Stein, Mateusz Ochal, Ioana Adriana Moisoiu, Enrico Gerding, Raghu Ganti, Ting He, Tom La Porta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider an online resource allocation problem where tasks with specific values, sizes and resource requirements arrive dynamically over time, and have to be either serviced or rejected immediately. Reinforcement learning is a promising approach for this, but existing work on reinforcement learning has neglected that task owners may misreport their task requirements or values strategically when this is to their benefit. To address this, we apply mechanism design and propose a novel mechanism based on reinforcement learning that aims to maximise social welfare, is strategyproof and individually rational (i.e., truthful reporting and participation are incentivised). In experiments, we show that our algorithm achieves results that are typically within 90% of the optimal social welfare, while outperforming approaches that use fixed pricing (by up to 86% in specific cases).

Original languageEnglish (US)
Title of host publicationProceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020
EditorsBo An, Amal El Fallah Seghrouchni, Gita Sukthankar
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages1296-1304
Number of pages9
ISBN (Electronic)9781450375184
StatePublished - 2020
Event19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 - Virtual, Auckland, New Zealand
Duration: May 19 2020 → …

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume2020-May
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Conference

Conference19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020
CountryNew Zealand
CityVirtual, Auckland
Period5/19/20 → …

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'Strategyproof reinforcement learning for online resource allocation'. Together they form a unique fingerprint.

Cite this