Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308285222> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4308285222 abstract "We study combinatorial problems with real world applications such as machine scheduling, routing, and assignment. We propose a method that combines Reinforcement Learning (RL) and planning. This method can equally be applied to both the offline, as well as online, variants of the combinatorial problem, in which the problem components (e.g., jobs in scheduling problems) are not known in advance, but rather arrive during the decision-making process. Our solution is quite generic, scalable, and leverages distributional knowledge of the problem parameters. We frame the solution process as an MDP, and take a Deep Q-Learning approach wherein states are represented as graphs, thereby allowing our trained policies to deal with arbitrary changes in a principled manner. Though learned policies work well in expectation, small deviations can have substantial negative effects in combinatorial settings. We mitigate these drawbacks by employing our graph-convolutional policies as non-optimal heuristics in a compatible search algorithm, Monte Carlo Tree Search, to significantly improve overall performance. We demonstrate our method on two problems: Machine Scheduling and Capacitated Vehicle Routing. We show that our method outperforms custom-tailored mathematical solvers, state of the art learning-based algorithms, and common heuristics, both in computation time and performance." @default.
- W4308285222 created "2022-11-10" @default.
- W4308285222 creator A5007065170 @default.
- W4308285222 creator A5009996777 @default.
- W4308285222 creator A5022378999 @default.
- W4308285222 creator A5023063165 @default.
- W4308285222 creator A5032709945 @default.
- W4308285222 creator A5047982234 @default.
- W4308285222 creator A5054078996 @default.
- W4308285222 creator A5066032921 @default.
- W4308285222 date "2021-04-04" @default.
- W4308285222 modified "2023-09-30" @default.
- W4308285222 title "SOLO: Search Online, Learn Offline for Combinatorial Optimization Problems" @default.
- W4308285222 doi "https://doi.org/10.48550/arxiv.2104.01646" @default.
- W4308285222 hasPublicationYear "2021" @default.
- W4308285222 type Work @default.
- W4308285222 citedByCount "0" @default.
- W4308285222 crossrefType "posted-content" @default.
- W4308285222 hasAuthorship W4308285222A5007065170 @default.
- W4308285222 hasAuthorship W4308285222A5009996777 @default.
- W4308285222 hasAuthorship W4308285222A5022378999 @default.
- W4308285222 hasAuthorship W4308285222A5023063165 @default.
- W4308285222 hasAuthorship W4308285222A5032709945 @default.
- W4308285222 hasAuthorship W4308285222A5047982234 @default.
- W4308285222 hasAuthorship W4308285222A5054078996 @default.
- W4308285222 hasAuthorship W4308285222A5066032921 @default.
- W4308285222 hasBestOaLocation W43082852221 @default.
- W4308285222 hasConcept C105795698 @default.
- W4308285222 hasConcept C111919701 @default.
- W4308285222 hasConcept C11413529 @default.
- W4308285222 hasConcept C119857082 @default.
- W4308285222 hasConcept C126255220 @default.
- W4308285222 hasConcept C127705205 @default.
- W4308285222 hasConcept C154945302 @default.
- W4308285222 hasConcept C163239763 @default.
- W4308285222 hasConcept C19499675 @default.
- W4308285222 hasConcept C206729178 @default.
- W4308285222 hasConcept C33923547 @default.
- W4308285222 hasConcept C41008148 @default.
- W4308285222 hasConcept C46149586 @default.
- W4308285222 hasConcept C48044578 @default.
- W4308285222 hasConcept C52692508 @default.
- W4308285222 hasConcept C59919655 @default.
- W4308285222 hasConcept C77088390 @default.
- W4308285222 hasConcept C80444323 @default.
- W4308285222 hasConcept C97541855 @default.
- W4308285222 hasConceptScore W4308285222C105795698 @default.
- W4308285222 hasConceptScore W4308285222C111919701 @default.
- W4308285222 hasConceptScore W4308285222C11413529 @default.
- W4308285222 hasConceptScore W4308285222C119857082 @default.
- W4308285222 hasConceptScore W4308285222C126255220 @default.
- W4308285222 hasConceptScore W4308285222C127705205 @default.
- W4308285222 hasConceptScore W4308285222C154945302 @default.
- W4308285222 hasConceptScore W4308285222C163239763 @default.
- W4308285222 hasConceptScore W4308285222C19499675 @default.
- W4308285222 hasConceptScore W4308285222C206729178 @default.
- W4308285222 hasConceptScore W4308285222C33923547 @default.
- W4308285222 hasConceptScore W4308285222C41008148 @default.
- W4308285222 hasConceptScore W4308285222C46149586 @default.
- W4308285222 hasConceptScore W4308285222C48044578 @default.
- W4308285222 hasConceptScore W4308285222C52692508 @default.
- W4308285222 hasConceptScore W4308285222C59919655 @default.
- W4308285222 hasConceptScore W4308285222C77088390 @default.
- W4308285222 hasConceptScore W4308285222C80444323 @default.
- W4308285222 hasConceptScore W4308285222C97541855 @default.
- W4308285222 hasLocation W43082852221 @default.
- W4308285222 hasLocation W43082852222 @default.
- W4308285222 hasOpenAccess W4308285222 @default.
- W4308285222 hasPrimaryLocation W43082852221 @default.
- W4308285222 hasRelatedWork W1992741870 @default.
- W4308285222 hasRelatedWork W2389719923 @default.
- W4308285222 hasRelatedWork W2546696010 @default.
- W4308285222 hasRelatedWork W3009304813 @default.
- W4308285222 hasRelatedWork W3022038857 @default.
- W4308285222 hasRelatedWork W3024399153 @default.
- W4308285222 hasRelatedWork W3152322648 @default.
- W4308285222 hasRelatedWork W3170112077 @default.
- W4308285222 hasRelatedWork W4308285222 @default.
- W4308285222 hasRelatedWork W4319083788 @default.
- W4308285222 isParatext "false" @default.
- W4308285222 isRetracted "false" @default.
- W4308285222 workType "article" @default.