Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management
In this paper, we consider the inventory management (IM) problem where we need to make replenishment decisions for a large number of stock keeping units (SKUs) to balance their supply and demand. In our setting, the constraint on the shared resources (such as the inventory capacity) couples the othe...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Ding, Yuandong Feng, Mingxiao Liu, Guozi Jiang, Wei Zhang, Chuheng Zhao, Li Song, Lei Li, Houqiang Jin, Yan Bian, Jiang |
| description | In this paper, we consider the inventory management (IM) problem where we
need to make replenishment decisions for a large number of stock keeping units
(SKUs) to balance their supply and demand. In our setting, the constraint on
the shared resources (such as the inventory capacity) couples the otherwise
independent control for each SKU. We formulate the problem with this structure
as Shared-Resource Stochastic Game (SRSG)and propose an efficient algorithm
called Context-aware Decentralized PPO (CD-PPO). Through extensive experiments,
we demonstrate that CD-PPO can accelerate the learning procedure compared with
standard MARL algorithms. |
| doi_str_mv | 10.48550/arxiv.2212.07684 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2212_07684</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2212_07684</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-8adc9a9f72bc8ee48091bfbed52b9f960a23832161567a1c7a317c866b26d2303</originalsourceid><addsrcrecordid>eNotj8tuwjAURL3poqL9gK7qH0jqR-LHEiHaIgUhKPvo2rGDJXCQE2j5-4a0q9FIZ0Y6CL1QkheqLMkbpJ9wzRmjLCdSqOIRbdeX4xCyeevigHcuRN8l6073VjlIMcQWf4fhgL8OkFwzIn13GYkejyBexetIdumG1xChnXZP6MHDsXfP_zlD-_flfvGZVZuP1WJeZSBkkSlorAbtJTNWOVcooqnxxjUlM9prQYBxxRkVtBQSqJXAqbRKCMNEwzjhM_T6dzs51ecUTpBu9d2tntz4L_dBSjY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management</title><source>arXiv.org</source><creator>Ding, Yuandong ; Feng, Mingxiao ; Liu, Guozi ; Jiang, Wei ; Zhang, Chuheng ; Zhao, Li ; Song, Lei ; Li, Houqiang ; Jin, Yan ; Bian, Jiang</creator><creatorcontrib>Ding, Yuandong ; Feng, Mingxiao ; Liu, Guozi ; Jiang, Wei ; Zhang, Chuheng ; Zhao, Li ; Song, Lei ; Li, Houqiang ; Jin, Yan ; Bian, Jiang</creatorcontrib><description>In this paper, we consider the inventory management (IM) problem where we
need to make replenishment decisions for a large number of stock keeping units
(SKUs) to balance their supply and demand. In our setting, the constraint on
the shared resources (such as the inventory capacity) couples the otherwise
independent control for each SKU. We formulate the problem with this structure
as Shared-Resource Stochastic Game (SRSG)and propose an efficient algorithm
called Context-aware Decentralized PPO (CD-PPO). Through extensive experiments,
we demonstrate that CD-PPO can accelerate the learning procedure compared with
standard MARL algorithms.</description><identifier>DOI: 10.48550/arxiv.2212.07684</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Mathematics - Optimization and Control</subject><creationdate>2022-12</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2212.07684$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2212.07684$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ding, Yuandong</creatorcontrib><creatorcontrib>Feng, Mingxiao</creatorcontrib><creatorcontrib>Liu, Guozi</creatorcontrib><creatorcontrib>Jiang, Wei</creatorcontrib><creatorcontrib>Zhang, Chuheng</creatorcontrib><creatorcontrib>Zhao, Li</creatorcontrib><creatorcontrib>Song, Lei</creatorcontrib><creatorcontrib>Li, Houqiang</creatorcontrib><creatorcontrib>Jin, Yan</creatorcontrib><creatorcontrib>Bian, Jiang</creatorcontrib><title>Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management</title><description>In this paper, we consider the inventory management (IM) problem where we
need to make replenishment decisions for a large number of stock keeping units
(SKUs) to balance their supply and demand. In our setting, the constraint on
the shared resources (such as the inventory capacity) couples the otherwise
independent control for each SKU. We formulate the problem with this structure
as Shared-Resource Stochastic Game (SRSG)and propose an efficient algorithm
called Context-aware Decentralized PPO (CD-PPO). Through extensive experiments,
we demonstrate that CD-PPO can accelerate the learning procedure compared with
standard MARL algorithms.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Mathematics - Optimization and Control</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tuwjAURL3poqL9gK7qH0jqR-LHEiHaIgUhKPvo2rGDJXCQE2j5-4a0q9FIZ0Y6CL1QkheqLMkbpJ9wzRmjLCdSqOIRbdeX4xCyeevigHcuRN8l6073VjlIMcQWf4fhgL8OkFwzIn13GYkejyBexetIdumG1xChnXZP6MHDsXfP_zlD-_flfvGZVZuP1WJeZSBkkSlorAbtJTNWOVcooqnxxjUlM9prQYBxxRkVtBQSqJXAqbRKCMNEwzjhM_T6dzs51ecUTpBu9d2tntz4L_dBSjY</recordid><startdate>20221215</startdate><enddate>20221215</enddate><creator>Ding, Yuandong</creator><creator>Feng, Mingxiao</creator><creator>Liu, Guozi</creator><creator>Jiang, Wei</creator><creator>Zhang, Chuheng</creator><creator>Zhao, Li</creator><creator>Song, Lei</creator><creator>Li, Houqiang</creator><creator>Jin, Yan</creator><creator>Bian, Jiang</creator><scope>AKY</scope><scope>AKZ</scope><scope>GOX</scope></search><sort><creationdate>20221215</creationdate><title>Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management</title><author>Ding, Yuandong ; Feng, Mingxiao ; Liu, Guozi ; Jiang, Wei ; Zhang, Chuheng ; Zhao, Li ; Song, Lei ; Li, Houqiang ; Jin, Yan ; Bian, Jiang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-8adc9a9f72bc8ee48091bfbed52b9f960a23832161567a1c7a317c866b26d2303</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Mathematics - Optimization and Control</topic><toplevel>online_resources</toplevel><creatorcontrib>Ding, Yuandong</creatorcontrib><creatorcontrib>Feng, Mingxiao</creatorcontrib><creatorcontrib>Liu, Guozi</creatorcontrib><creatorcontrib>Jiang, Wei</creatorcontrib><creatorcontrib>Zhang, Chuheng</creatorcontrib><creatorcontrib>Zhao, Li</creatorcontrib><creatorcontrib>Song, Lei</creatorcontrib><creatorcontrib>Li, Houqiang</creatorcontrib><creatorcontrib>Jin, Yan</creatorcontrib><creatorcontrib>Bian, Jiang</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Mathematics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ding, Yuandong</au><au>Feng, Mingxiao</au><au>Liu, Guozi</au><au>Jiang, Wei</au><au>Zhang, Chuheng</au><au>Zhao, Li</au><au>Song, Lei</au><au>Li, Houqiang</au><au>Jin, Yan</au><au>Bian, Jiang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management</atitle><date>2022-12-15</date><risdate>2022</risdate><abstract>In this paper, we consider the inventory management (IM) problem where we
need to make replenishment decisions for a large number of stock keeping units
(SKUs) to balance their supply and demand. In our setting, the constraint on
the shared resources (such as the inventory capacity) couples the otherwise
independent control for each SKU. We formulate the problem with this structure
as Shared-Resource Stochastic Game (SRSG)and propose an efficient algorithm
called Context-aware Decentralized PPO (CD-PPO). Through extensive experiments,
we demonstrate that CD-PPO can accelerate the learning procedure compared with
standard MARL algorithms.</abstract><doi>10.48550/arxiv.2212.07684</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2212.07684 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2212_07684 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Learning Mathematics - Optimization and Control |
| title | Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T14%3A06%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multi-Agent%20Reinforcement%20Learning%20with%20Shared%20Resources%20for%20Inventory%20Management&rft.au=Ding,%20Yuandong&rft.date=2022-12-15&rft_id=info:doi/10.48550/arxiv.2212.07684&rft_dat=%3Carxiv_GOX%3E2212_07684%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |