abstracts[] |
{'sha1': '5a4f6b05c589dffcebbdadbb54f9bccb66009f82', 'content': 'In a warehouse environment, tasks appear dynamically. Consequently, a task\nmanagement system that matches them with the workforce too early (e.g., weeks\nin advance) is necessarily sub-optimal. Also, the rapidly increasing size of\nthe action space of such a system consists of a significant problem for\ntraditional schedulers. Reinforcement learning, however, is suited to deal with\nissues requiring making sequential decisions towards a long-term, often remote,\ngoal. In this work, we set ourselves on a problem that presents itself with a\nhierarchical structure: the task-scheduling, by a centralised agent, in a\ndynamic warehouse multi-agent environment and the execution of one such\nschedule, by decentralised agents with only partial observability thereof. We\npropose to use deep reinforcement learning to solve both the high-level\nscheduling problem and the low-level multi-agent problem of schedule execution.\nFinally, we also conceive the case where centralisation is impossible at test\ntime and workers must learn how to cooperate in executing the tasks in an\nenvironment with no schedule and only partial observability.', 'mimetype': 'text/plain', 'lang': 'en'}
|
container |
|
container_id |
|
contribs[] |
{'index': 0, 'creator_id': None, 'creator': None, 'raw_name': 'Diogo S. Carvalho', 'given_name': None, 'surname': None, 'role': 'author', 'raw_affiliation': None, 'extra': None}
{'index': 1, 'creator_id': None, 'creator': None, 'raw_name': 'Biswa Sengupta', 'given_name': None, 'surname': None, 'role': 'author', 'raw_affiliation': None, 'extra': None}
|
ext_ids |
{'doi': None, 'wikidata_qid': None, 'isbn13': None, 'pmid': None, 'pmcid': None, 'core': None, 'arxiv': '2203.03021v1', 'jstor': None, 'ark': None, 'mag': None, 'doaj': None, 'dblp': None, 'oai': None, 'hdl': None}
|
files[] |
{'state': 'active', 'ident': 'tvdn72lle5esxb3lazdtkrrbyy', 'revision': 'db6b9087-3592-408e-a490-79d8c0c683aa', 'redirect': None, 'extra': None, 'edit_extra': None, 'size': 627731, 'md5': 'ecd6f73ca9f99194591ff6c764fa5865', 'sha1': 'c5391d8109832acc8dc4ca2322725598bdaccde5', 'sha256': '023da1c908c1aece59fc85c702a12b04309e7f85ed38e1342c87587c2f493ed8', 'urls': [{'url': 'https://arxiv.org/pdf/2203.03021v1.pdf', 'rel': 'repository'}, {'url': 'https://web.archive.org/web/20220310105842/https://arxiv.org/pdf/2203.03021v1.pdf', 'rel': 'webarchive'}], 'mimetype': 'application/pdf', 'content_scope': None, 'release_ids': ['undob22rivgbncl2bxddshbhja'], 'releases': None}
|
filesets |
[]
|
issue |
|
language |
en
|
license_slug |
CC-BY-NC-ND
|
number |
|
original_title |
|
pages |
|
publisher |
|
refs |
[]
|
release_date |
2022-03-06
|
release_stage |
submitted
|
release_type |
article
|
release_year |
2022
|
subtitle |
|
title |
Hierarchically Structured Scheduling and Execution of Tasks in a Multi-Agent Environment
|
version |
v1
|
volume |
|
webcaptures |
[]
|
withdrawn_date |
|
withdrawn_status |
|
withdrawn_year |
|
work_id |
pvhiuupr2jhqtc7k42hxxobmnm
|