Matches in SemOpenAlex for { <https://semopenalex.org/work/W3010220509> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3010220509 abstract "We consider the problem of an operator controlling a fleet of electric vehicles for use in a ridehailing service. The operator, seeking to maximize revenue, must assign vehicles to requests as they arise and recharge and reposition vehicles in anticipation of future requests. To solve this problem, we employ deep reinforcement learning, developing policies whose decision making uses Q-value approximations learned by deep neural networks. We compare these policies against a common taxi dispatching heuristic and against dual bounds on the value of an optimal policy, including the value of an optimal policy with perfect information which we establish using a Benders-based decomposition. We assess performance on instances derived from real data for the island of Manhattan in New York City. We find that, across instances of varying size, our best policy trained with deep reinforcement learning outperforms the taxi dispatching heuristic. We also provide evidence that this policy may be effectively scaled and deployed on larger instances without retraining." @default.
- W3010220509 created "2020-03-13" @default.
- W3010220509 creator A5005378724 @default.
- W3010220509 creator A5015657270 @default.
- W3010220509 creator A5079163907 @default.
- W3010220509 creator A5079497200 @default.
- W3010220509 date "2021-07-29" @default.
- W3010220509 modified "2023-09-23" @default.
- W3010220509 title "Dynamic Ridehailing with Electric Vehicles" @default.
- W3010220509 cites W1595882479 @default.
- W3010220509 cites W2103253102 @default.
- W3010220509 cites W2140491322 @default.
- W3010220509 cites W2141559645 @default.
- W3010220509 cites W2155968351 @default.
- W3010220509 cites W2173564293 @default.
- W3010220509 cites W2255469947 @default.
- W3010220509 cites W2357730318 @default.
- W3010220509 cites W2569460227 @default.
- W3010220509 cites W2593704234 @default.
- W3010220509 cites W2756327937 @default.
- W3010220509 cites W2761873684 @default.
- W3010220509 cites W2783866702 @default.
- W3010220509 cites W2792987450 @default.
- W3010220509 cites W2803952469 @default.
- W3010220509 cites W2905126357 @default.
- W3010220509 cites W2909640002 @default.
- W3010220509 cites W2944404766 @default.
- W3010220509 cites W2946570440 @default.
- W3010220509 cites W2951527505 @default.
- W3010220509 cites W2963477884 @default.
- W3010220509 cites W2964571806 @default.
- W3010220509 cites W2982455172 @default.
- W3010220509 cites W316935178 @default.
- W3010220509 cites W855132903 @default.
- W3010220509 hasPublicationYear "2021" @default.
- W3010220509 type Work @default.
- W3010220509 sameAs 3010220509 @default.
- W3010220509 citedByCount "3" @default.
- W3010220509 countsByYear W30102205092020 @default.
- W3010220509 countsByYear W30102205092021 @default.
- W3010220509 crossrefType "journal-article" @default.
- W3010220509 hasAuthorship W3010220509A5005378724 @default.
- W3010220509 hasAuthorship W3010220509A5015657270 @default.
- W3010220509 hasAuthorship W3010220509A5079163907 @default.
- W3010220509 hasAuthorship W3010220509A5079497200 @default.
- W3010220509 hasBestOaLocation W30102205091 @default.
- W3010220509 hasConcept C127413603 @default.
- W3010220509 hasConcept C171146098 @default.
- W3010220509 hasConcept C178802073 @default.
- W3010220509 hasConcept C41008148 @default.
- W3010220509 hasConceptScore W3010220509C127413603 @default.
- W3010220509 hasConceptScore W3010220509C171146098 @default.
- W3010220509 hasConceptScore W3010220509C178802073 @default.
- W3010220509 hasConceptScore W3010220509C41008148 @default.
- W3010220509 hasLocation W30102205091 @default.
- W3010220509 hasLocation W30102205092 @default.
- W3010220509 hasLocation W30102205093 @default.
- W3010220509 hasLocation W30102205094 @default.
- W3010220509 hasOpenAccess W3010220509 @default.
- W3010220509 hasPrimaryLocation W30102205091 @default.
- W3010220509 hasRelatedWork W1596801655 @default.
- W3010220509 hasRelatedWork W2130043461 @default.
- W3010220509 hasRelatedWork W2350741829 @default.
- W3010220509 hasRelatedWork W2358668433 @default.
- W3010220509 hasRelatedWork W2376932109 @default.
- W3010220509 hasRelatedWork W2382290278 @default.
- W3010220509 hasRelatedWork W2390279801 @default.
- W3010220509 hasRelatedWork W2748952813 @default.
- W3010220509 hasRelatedWork W2899084033 @default.
- W3010220509 hasRelatedWork W2530322880 @default.
- W3010220509 isParatext "false" @default.
- W3010220509 isRetracted "false" @default.
- W3010220509 magId "3010220509" @default.
- W3010220509 workType "article" @default.