Matches in SemOpenAlex for { <https://semopenalex.org/work/W3140147451> ?p ?o ?g. }
- W3140147451 endingPage "4559" @default.
- W3140147451 startingPage "4552" @default.
- W3140147451 abstract "Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omni-directional target with multiple, homogeneous agents that are subject to unicycle kinematic constraints. We use shared experience to train a policy for a given number of pursuers that is executed independently by each agent at run-time. The training benefits from curriculum learning, a sweeping-angle ordering to locally represent neighboring agents and encouraging good formations with reward structure that combines individual and group rewards. Simulated experiments with a reactive evader and up to eight pursuers show that our learning-based approach, with non-holonomic agents, performs on par with classical algorithms with omni-directional agents, and outperforms their non-holonomic adaptations. The learned policy is successfully transferred to the real world in a proof-of-concept demonstration with three motion-constrained pursuer drones." @default.
- W3140147451 created "2021-04-13" @default.
- W3140147451 creator A5009291465 @default.
- W3140147451 creator A5011941487 @default.
- W3140147451 creator A5016466454 @default.
- W3140147451 creator A5017742052 @default.
- W3140147451 creator A5028574557 @default.
- W3140147451 creator A5033558251 @default.
- W3140147451 date "2021-07-01" @default.
- W3140147451 modified "2023-10-16" @default.
- W3140147451 title "Decentralized Multi-Agent Pursuit Using Deep Reinforcement Learning" @default.
- W3140147451 cites W1672238326 @default.
- W3140147451 cites W1677859417 @default.
- W3140147451 cites W2015410655 @default.
- W3140147451 cites W2016437006 @default.
- W3140147451 cites W2020778932 @default.
- W3140147451 cites W2023775503 @default.
- W3140147451 cites W2050044094 @default.
- W3140147451 cites W2105850748 @default.
- W3140147451 cites W2131774270 @default.
- W3140147451 cites W2296073425 @default.
- W3140147451 cites W2305205647 @default.
- W3140147451 cites W2331855880 @default.
- W3140147451 cites W2498529546 @default.
- W3140147451 cites W2502930595 @default.
- W3140147451 cites W2528107617 @default.
- W3140147451 cites W2567355071 @default.
- W3140147451 cites W2772042733 @default.
- W3140147451 cites W2889656043 @default.
- W3140147451 cites W2909445258 @default.
- W3140147451 cites W2949447421 @default.
- W3140147451 cites W2963099939 @default.
- W3140147451 cites W2972273284 @default.
- W3140147451 cites W2990123902 @default.
- W3140147451 cites W3005152498 @default.
- W3140147451 cites W3040707741 @default.
- W3140147451 cites W40650588 @default.
- W3140147451 cites W4230799304 @default.
- W3140147451 doi "https://doi.org/10.1109/lra.2021.3068952" @default.
- W3140147451 hasPublicationYear "2021" @default.
- W3140147451 type Work @default.
- W3140147451 sameAs 3140147451 @default.
- W3140147451 citedByCount "39" @default.
- W3140147451 countsByYear W31401474512021 @default.
- W3140147451 countsByYear W31401474512022 @default.
- W3140147451 countsByYear W31401474512023 @default.
- W3140147451 crossrefType "journal-article" @default.
- W3140147451 hasAuthorship W3140147451A5009291465 @default.
- W3140147451 hasAuthorship W3140147451A5011941487 @default.
- W3140147451 hasAuthorship W3140147451A5016466454 @default.
- W3140147451 hasAuthorship W3140147451A5017742052 @default.
- W3140147451 hasAuthorship W3140147451A5028574557 @default.
- W3140147451 hasAuthorship W3140147451A5033558251 @default.
- W3140147451 hasBestOaLocation W31401474513 @default.
- W3140147451 hasConcept C104114177 @default.
- W3140147451 hasConcept C114614502 @default.
- W3140147451 hasConcept C119857082 @default.
- W3140147451 hasConcept C121332964 @default.
- W3140147451 hasConcept C126255220 @default.
- W3140147451 hasConcept C1276947 @default.
- W3140147451 hasConcept C13662910 @default.
- W3140147451 hasConcept C144024400 @default.
- W3140147451 hasConcept C154945302 @default.
- W3140147451 hasConcept C2776927521 @default.
- W3140147451 hasConcept C2777964439 @default.
- W3140147451 hasConcept C2778388243 @default.
- W3140147451 hasConcept C2779304628 @default.
- W3140147451 hasConcept C33923547 @default.
- W3140147451 hasConcept C36289849 @default.
- W3140147451 hasConcept C39920418 @default.
- W3140147451 hasConcept C41008148 @default.
- W3140147451 hasConcept C54355233 @default.
- W3140147451 hasConcept C59519942 @default.
- W3140147451 hasConcept C66882249 @default.
- W3140147451 hasConcept C74650414 @default.
- W3140147451 hasConcept C86803240 @default.
- W3140147451 hasConcept C97541855 @default.
- W3140147451 hasConceptScore W3140147451C104114177 @default.
- W3140147451 hasConceptScore W3140147451C114614502 @default.
- W3140147451 hasConceptScore W3140147451C119857082 @default.
- W3140147451 hasConceptScore W3140147451C121332964 @default.
- W3140147451 hasConceptScore W3140147451C126255220 @default.
- W3140147451 hasConceptScore W3140147451C1276947 @default.
- W3140147451 hasConceptScore W3140147451C13662910 @default.
- W3140147451 hasConceptScore W3140147451C144024400 @default.
- W3140147451 hasConceptScore W3140147451C154945302 @default.
- W3140147451 hasConceptScore W3140147451C2776927521 @default.
- W3140147451 hasConceptScore W3140147451C2777964439 @default.
- W3140147451 hasConceptScore W3140147451C2778388243 @default.
- W3140147451 hasConceptScore W3140147451C2779304628 @default.
- W3140147451 hasConceptScore W3140147451C33923547 @default.
- W3140147451 hasConceptScore W3140147451C36289849 @default.
- W3140147451 hasConceptScore W3140147451C39920418 @default.
- W3140147451 hasConceptScore W3140147451C41008148 @default.
- W3140147451 hasConceptScore W3140147451C54355233 @default.
- W3140147451 hasConceptScore W3140147451C59519942 @default.
- W3140147451 hasConceptScore W3140147451C66882249 @default.
- W3140147451 hasConceptScore W3140147451C74650414 @default.