Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference
When a robot autonomously performs a complex task, it frequently must balance competing objectives while maintaining safety. This becomes more difficult in uncertain environments with stochastic outcomes. Enhancing transparency in the robot's behavior and aligning with user preferences are also...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-06 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Amorese, Peter Wakayama, Shohei Nisar, Ahmed Lahijanian, Morteza |
description | When a robot autonomously performs a complex task, it frequently must balance competing objectives while maintaining safety. This becomes more difficult in uncertain environments with stochastic outcomes. Enhancing transparency in the robot's behavior and aligning with user preferences are also crucial. This paper introduces a novel framework for multi-objective reinforcement learning that ensures safe task execution, optimizes trade-offs between objectives, and adheres to user preferences. The framework has two main layers: a multi-objective task planner and a high-level selector. The planning layer generates a set of optimal trade-off plans that guarantee satisfaction of a temporal logic task. The selector uses active inference to decide which generated plan best complies with user preferences and aids learning. Operating iteratively, the framework updates a parameterized learning model based on collected data. Case studies and benchmarks on both manipulation and mobile robots show that our framework outperforms other methods and (i) learns multiple optimal trade-offs, (ii) adheres to a user preference, and (iii) allows the user to adjust the balance between (i) and (ii). |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3069649843</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3069649843</sourcerecordid><originalsourceid>FETCH-proquest_journals_30696498433</originalsourceid><addsrcrecordid>eNqNikELgjAYQEcQJOV_GHQerE1Nj2FFHcoO3mXIZ0znZvs0-vkV9AM6PXjvzUggpNywNBJiQULElnMukq2IYxmQa2GNtkBvysPoWDGMuleG7qHWqJ1lF9Vpe6eN8zR3_WDgRUuFHdIJv35Xj_oJ9Gwb8GBrWJF5owxC-OOSrI-HMj-xwbvHBDhWrZu8_aRK8iRLoiyNpPzvegOrHD32</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3069649843</pqid></control><display><type>article</type><title>Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference</title><source>Free E- Journals</source><creator>Amorese, Peter ; Wakayama, Shohei ; Nisar, Ahmed ; Lahijanian, Morteza</creator><creatorcontrib>Amorese, Peter ; Wakayama, Shohei ; Nisar, Ahmed ; Lahijanian, Morteza</creatorcontrib><description>When a robot autonomously performs a complex task, it frequently must balance competing objectives while maintaining safety. This becomes more difficult in uncertain environments with stochastic outcomes. Enhancing transparency in the robot's behavior and aligning with user preferences are also crucial. This paper introduces a novel framework for multi-objective reinforcement learning that ensures safe task execution, optimizes trade-offs between objectives, and adheres to user preferences. The framework has two main layers: a multi-objective task planner and a high-level selector. The planning layer generates a set of optimal trade-off plans that guarantee satisfaction of a temporal logic task. The selector uses active inference to decide which generated plan best complies with user preferences and aids learning. Operating iteratively, the framework updates a parameterized learning model based on collected data. Case studies and benchmarks on both manipulation and mobile robots show that our framework outperforms other methods and (i) learns multiple optimal trade-offs, (ii) adheres to a user preference, and (iii) allows the user to adjust the balance between (i) and (ii).</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Inference ; Multiple objective analysis ; Robots ; Task complexity ; Temporal logic ; Tradeoffs</subject><ispartof>arXiv.org, 2024-06</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Amorese, Peter</creatorcontrib><creatorcontrib>Wakayama, Shohei</creatorcontrib><creatorcontrib>Nisar, Ahmed</creatorcontrib><creatorcontrib>Lahijanian, Morteza</creatorcontrib><title>Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference</title><title>arXiv.org</title><description>When a robot autonomously performs a complex task, it frequently must balance competing objectives while maintaining safety. This becomes more difficult in uncertain environments with stochastic outcomes. Enhancing transparency in the robot's behavior and aligning with user preferences are also crucial. This paper introduces a novel framework for multi-objective reinforcement learning that ensures safe task execution, optimizes trade-offs between objectives, and adheres to user preferences. The framework has two main layers: a multi-objective task planner and a high-level selector. The planning layer generates a set of optimal trade-off plans that guarantee satisfaction of a temporal logic task. The selector uses active inference to decide which generated plan best complies with user preferences and aids learning. Operating iteratively, the framework updates a parameterized learning model based on collected data. Case studies and benchmarks on both manipulation and mobile robots show that our framework outperforms other methods and (i) learns multiple optimal trade-offs, (ii) adheres to a user preference, and (iii) allows the user to adjust the balance between (i) and (ii).</description><subject>Inference</subject><subject>Multiple objective analysis</subject><subject>Robots</subject><subject>Task complexity</subject><subject>Temporal logic</subject><subject>Tradeoffs</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNikELgjAYQEcQJOV_GHQerE1Nj2FFHcoO3mXIZ0znZvs0-vkV9AM6PXjvzUggpNywNBJiQULElnMukq2IYxmQa2GNtkBvysPoWDGMuleG7qHWqJ1lF9Vpe6eN8zR3_WDgRUuFHdIJv35Xj_oJ9Gwb8GBrWJF5owxC-OOSrI-HMj-xwbvHBDhWrZu8_aRK8iRLoiyNpPzvegOrHD32</recordid><startdate>20240617</startdate><enddate>20240617</enddate><creator>Amorese, Peter</creator><creator>Wakayama, Shohei</creator><creator>Nisar, Ahmed</creator><creator>Lahijanian, Morteza</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240617</creationdate><title>Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference</title><author>Amorese, Peter ; Wakayama, Shohei ; Nisar, Ahmed ; Lahijanian, Morteza</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30696498433</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Inference</topic><topic>Multiple objective analysis</topic><topic>Robots</topic><topic>Task complexity</topic><topic>Temporal logic</topic><topic>Tradeoffs</topic><toplevel>online_resources</toplevel><creatorcontrib>Amorese, Peter</creatorcontrib><creatorcontrib>Wakayama, Shohei</creatorcontrib><creatorcontrib>Nisar, Ahmed</creatorcontrib><creatorcontrib>Lahijanian, Morteza</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Amorese, Peter</au><au>Wakayama, Shohei</au><au>Nisar, Ahmed</au><au>Lahijanian, Morteza</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference</atitle><jtitle>arXiv.org</jtitle><date>2024-06-17</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>When a robot autonomously performs a complex task, it frequently must balance competing objectives while maintaining safety. This becomes more difficult in uncertain environments with stochastic outcomes. Enhancing transparency in the robot's behavior and aligning with user preferences are also crucial. This paper introduces a novel framework for multi-objective reinforcement learning that ensures safe task execution, optimizes trade-offs between objectives, and adheres to user preferences. The framework has two main layers: a multi-objective task planner and a high-level selector. The planning layer generates a set of optimal trade-off plans that guarantee satisfaction of a temporal logic task. The selector uses active inference to decide which generated plan best complies with user preferences and aids learning. Operating iteratively, the framework updates a parameterized learning model based on collected data. Case studies and benchmarks on both manipulation and mobile robots show that our framework outperforms other methods and (i) learns multiple optimal trade-offs, (ii) adheres to a user preference, and (iii) allows the user to adjust the balance between (i) and (ii).</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-06 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3069649843 |
source | Free E- Journals |
subjects | Inference Multiple objective analysis Robots Task complexity Temporal logic Tradeoffs |
title | Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T11%3A50%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Online%20Pareto-Optimal%20Decision-Making%20for%20Complex%20Tasks%20using%20Active%20Inference&rft.jtitle=arXiv.org&rft.au=Amorese,%20Peter&rft.date=2024-06-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3069649843%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3069649843&rft_id=info:pmid/&rfr_iscdi=true |