Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387363963> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4387363963 endingPage "101787" @default.
- W4387363963 startingPage "101787" @default.
- W4387363963 abstract "Deep reinforcement learning (DRL) has shown promise in solving challenging combinatorial optimization (CO) problems, such as the traveling salesman problem (TSP) and vehicle routing problem (VRP). However, existing DRL methods rely on manually designed reward functions, which may be inaccurate or unrealistic. Moreover, traditional DRL algorithms suffer from unstable training and sparse reward problems. This paper proposes GIRL (Generative Inverse Reinforcement Learning), a method to learn 2-opt heuristics without explicit extrinsic rewards to address these limitations. GIRL combines generative adversarial networks (GANs) and DRL to learn effective policies and reward functions in a reverse end-to-end fashion, improving generalization capabilities. Furthermore, we introduce a self-attentional policy network tailored for 2-opt heuristics and train the framework using a soft actor-critic algorithm along with a discriminator in the GAN. Extensive experiments on various TSP and VRP instances demonstrate superior performance compared to state-of-the-art methods. Moreover, integrating GANs and DRL enables data-driven reward functions, improving accuracy and realism. Using self-attentional networks and the soft actor-critic algorithm enhances training stability and addresses the sparse reward problem. This work advances reinforcement learning techniques in CO, enabling more accurate and practical optimization methods in real-world applications." @default.
- W4387363963 created "2023-10-06" @default.
- W4387363963 creator A5004645356 @default.
- W4387363963 creator A5077087945 @default.
- W4387363963 creator A5085545717 @default.
- W4387363963 date "2023-10-01" @default.
- W4387363963 modified "2023-10-18" @default.
- W4387363963 title "Generative Inverse Reinforcement Learning for Learning 2-opt Heuristics without Extrinsic Rewards in Routing Problems" @default.
- W4387363963 cites W1589747210 @default.
- W4387363963 cites W1597286183 @default.
- W4387363963 cites W2070469928 @default.
- W4387363963 cites W2102847492 @default.
- W4387363963 cites W2766447205 @default.
- W4387363963 cites W2919115771 @default.
- W4387363963 cites W2938157874 @default.
- W4387363963 cites W2963224980 @default.
- W4387363963 cites W2963607524 @default.
- W4387363963 cites W2997233328 @default.
- W4387363963 cites W2998327136 @default.
- W4387363963 cites W2998396902 @default.
- W4387363963 cites W3015128373 @default.
- W4387363963 cites W3047863327 @default.
- W4387363963 cites W3113123584 @default.
- W4387363963 cites W3129322645 @default.
- W4387363963 cites W3138984732 @default.
- W4387363963 cites W3146106549 @default.
- W4387363963 cites W3157439125 @default.
- W4387363963 cites W3170112077 @default.
- W4387363963 cites W3177318507 @default.
- W4387363963 cites W3185606095 @default.
- W4387363963 cites W3194071146 @default.
- W4387363963 cites W3202775986 @default.
- W4387363963 cites W4210257598 @default.
- W4387363963 cites W4226053965 @default.
- W4387363963 cites W4226177431 @default.
- W4387363963 cites W4242801005 @default.
- W4387363963 cites W4285606784 @default.
- W4387363963 cites W4285723986 @default.
- W4387363963 cites W4302010773 @default.
- W4387363963 cites W4309777438 @default.
- W4387363963 doi "https://doi.org/10.1016/j.jksuci.2023.101787" @default.
- W4387363963 hasPublicationYear "2023" @default.
- W4387363963 type Work @default.
- W4387363963 citedByCount "0" @default.
- W4387363963 crossrefType "journal-article" @default.
- W4387363963 hasAuthorship W4387363963A5004645356 @default.
- W4387363963 hasAuthorship W4387363963A5077087945 @default.
- W4387363963 hasAuthorship W4387363963A5085545717 @default.
- W4387363963 hasBestOaLocation W43873639631 @default.
- W4387363963 hasConcept C111919701 @default.
- W4387363963 hasConcept C119857082 @default.
- W4387363963 hasConcept C126255220 @default.
- W4387363963 hasConcept C127705205 @default.
- W4387363963 hasConcept C13280743 @default.
- W4387363963 hasConcept C134306372 @default.
- W4387363963 hasConcept C154945302 @default.
- W4387363963 hasConcept C177148314 @default.
- W4387363963 hasConcept C185798385 @default.
- W4387363963 hasConcept C205649164 @default.
- W4387363963 hasConcept C33923547 @default.
- W4387363963 hasConcept C39890363 @default.
- W4387363963 hasConcept C41008148 @default.
- W4387363963 hasConcept C97541855 @default.
- W4387363963 hasConceptScore W4387363963C111919701 @default.
- W4387363963 hasConceptScore W4387363963C119857082 @default.
- W4387363963 hasConceptScore W4387363963C126255220 @default.
- W4387363963 hasConceptScore W4387363963C127705205 @default.
- W4387363963 hasConceptScore W4387363963C13280743 @default.
- W4387363963 hasConceptScore W4387363963C134306372 @default.
- W4387363963 hasConceptScore W4387363963C154945302 @default.
- W4387363963 hasConceptScore W4387363963C177148314 @default.
- W4387363963 hasConceptScore W4387363963C185798385 @default.
- W4387363963 hasConceptScore W4387363963C205649164 @default.
- W4387363963 hasConceptScore W4387363963C33923547 @default.
- W4387363963 hasConceptScore W4387363963C39890363 @default.
- W4387363963 hasConceptScore W4387363963C41008148 @default.
- W4387363963 hasConceptScore W4387363963C97541855 @default.
- W4387363963 hasIssue "9" @default.
- W4387363963 hasLocation W43873639631 @default.
- W4387363963 hasOpenAccess W4387363963 @default.
- W4387363963 hasPrimaryLocation W43873639631 @default.
- W4387363963 hasRelatedWork W2130974462 @default.
- W4387363963 hasRelatedWork W2280422768 @default.
- W4387363963 hasRelatedWork W2378211422 @default.
- W4387363963 hasRelatedWork W3016293053 @default.
- W4387363963 hasRelatedWork W3121175838 @default.
- W4387363963 hasRelatedWork W3143197806 @default.
- W4387363963 hasRelatedWork W4252555497 @default.
- W4387363963 hasRelatedWork W4321353415 @default.
- W4387363963 hasRelatedWork W4377293004 @default.
- W4387363963 hasRelatedWork W972276598 @default.
- W4387363963 hasVolume "35" @default.
- W4387363963 isParatext "false" @default.
- W4387363963 isRetracted "false" @default.
- W4387363963 workType "article" @default.