Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Jonas K. Falkner"'
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783031264214
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4fd3f9113a735875607ab2617fb23be3
https://doi.org/10.1007/978-3-031-26422-1_31
https://doi.org/10.1007/978-3-031-26422-1_31
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783031264184
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ce1a7617cf01d5939a0251c917e4682f
https://doi.org/10.1007/978-3-031-26419-1_22
https://doi.org/10.1007/978-3-031-26419-1_22
Solving the Traveling Salesperson Problem with Precedence Constraints by Deep Reinforcement Learning
Autor:
Christian Löwens, Inaam Ashraf, Alexander Gembus, Genesis Cuizon, Jonas K. Falkner, Lars Schmidt-Thieme
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031157905
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e2d30cf78970333771a607d430da83c
https://doi.org/10.1007/978-3-031-15791-2_14
https://doi.org/10.1007/978-3-031-15791-2_14
Autor:
Jonas K. Falkner, Ahmad Bdeir, Lars Schmidt-Thieme, Kirill Tkachuk, Tim Dernedde, Simon Boeder
Publikováno v:
KI 2021: Advances in Artificial Intelligence ISBN: 9783030876258
KI
KI
In this paper we present a new approach to tackle complex routing problems with an improved state representation that utilizes the model complexity better than previous methods. We enable this by training from temporal differences. Specifically Q-Lea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a7b9ce6b8c087cb4d21de1291ddec0da
https://doi.org/10.1007/978-3-030-87626-5_1
https://doi.org/10.1007/978-3-030-87626-5_1
Publikováno v:
GECCO Companion
This paper introduces an innovative solution to the joint Order Batching - Order Picking Planning Problem. Previous research on this field has mainly focused on solving the two problems separately. Failing to consolidate the two components, however,