FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3148400014> ?p ?o ?g. }

• W3148400014 abstract "This paper introduces an adaptive model-free deep reinforcement approach that can recognize and adapt to the diurnal patterns in the ride-sharing environment with car-pooling. Deep Reinforcement Learning (RL) suffers from catastrophic forgetting due to being agnostic to the timescale of changes in the distribution of experiences. Although RL algorithms are guaranteed to converge to optimal policies in Markov decision processes (MDPs), this only holds in the presence of static environments. However, this assumption is very restrictive. In many real-world problems like ride-sharing, traffic control, etc., we are dealing with highly dynamic environments, where RL methods yield only sub-optimal decisions. To mitigate this problem in highly dynamic environments, we (1) adopt an online Dirichlet change point detection (ODCP) algorithm to detect the changes in the distribution of experiences, (2) develop a Deep Q Network (DQN) agent that is capable of recognizing diurnal patterns and making informed dispatching decisions according to the changes in the underlying environment. Rather than fixing patterns by time of week, the proposed approach automatically detects that the MDP has changed, and uses the results of the new model. In addition to the adaptation logic in dispatching, this paper also proposes a dynamic, demand-aware vehicle-passenger matching and route planning framework that dynamically generates optimal routes for each vehicle based on online demand, vehicle capacities, and locations. Evaluation on New York City Taxi public dataset shows the effectiveness of our approach in improving the fleet utilization, where less than 50% of the fleet are utilized to serve the demand of up to 90% of the requests, while maximizing profits and minimizing idle times." @default.
• W3148400014 created "2021-04-13" @default.
• W3148400014 creator A5024270752 @default.
• W3148400014 creator A5064822688 @default.
• W3148400014 creator A5077320731 @default.
• W3148400014 date "2021-04-01" @default.
• W3148400014 modified "2023-09-26" @default.
• W3148400014 title "AdaPool: A Diurnal-Adaptive Fleet Management Framework using Model-Free Deep Reinforcement Learning and Change Point Detection" @default.
• W3148400014 cites W1519626139 @default.
• W3148400014 cites W1682403713 @default.
• W3148400014 cites W1849095486 @default.
• W3148400014 cites W1965878388 @default.
• W3148400014 cites W1994917133 @default.
• W3148400014 cites W2019585788 @default.
• W3148400014 cites W2105834060 @default.
• W3148400014 cites W2122187689 @default.
• W3148400014 cites W2249371088 @default.
• W3148400014 cites W2344944957 @default.
• W3148400014 cites W2473930607 @default.
• W3148400014 cites W2552176588 @default.
• W3148400014 cites W2560647685 @default.
• W3148400014 cites W2565919573 @default.
• W3148400014 cites W2613597768 @default.
• W3148400014 cites W2615579321 @default.
• W3148400014 cites W2808786377 @default.
• W3148400014 cites W2885060261 @default.
• W3148400014 cites W2889125237 @default.
• W3148400014 cites W2915814342 @default.
• W3148400014 cites W2945119207 @default.
• W3148400014 cites W2962787188 @default.
• W3148400014 cites W2963560049 @default.
• W3148400014 cites W2964169391 @default.
• W3148400014 cites W2966818373 @default.
• W3148400014 cites W2968301466 @default.
• W3148400014 cites W2978949425 @default.
• W3148400014 cites W3008693879 @default.
• W3148400014 cites W3009669424 @default.
• W3148400014 cites W3013637982 @default.
• W3148400014 cites W3034038218 @default.
• W3148400014 cites W3035135748 @default.
• W3148400014 cites W3037675691 @default.
• W3148400014 cites W3040879766 @default.
• W3148400014 cites W3094541069 @default.
• W3148400014 cites W3102049471 @default.
• W3148400014 cites W3112032550 @default.
• W3148400014 cites W3125178068 @default.
• W3148400014 cites W3126940024 @default.
• W3148400014 cites W3168573009 @default.
• W3148400014 cites W3179601372 @default.
• W3148400014 hasPublicationYear "2021" @default.
• W3148400014 type Work @default.
• W3148400014 sameAs 3148400014 @default.
• W3148400014 citedByCount "0" @default.
• W3148400014 crossrefType "posted-content" @default.
• W3148400014 hasAuthorship W3148400014A5024270752 @default.
• W3148400014 hasAuthorship W3148400014A5064822688 @default.
• W3148400014 hasAuthorship W3148400014A5077320731 @default.
• W3148400014 hasConcept C105795698 @default.
• W3148400014 hasConcept C106189395 @default.
• W3148400014 hasConcept C120665830 @default.
• W3148400014 hasConcept C121332964 @default.
• W3148400014 hasConcept C126255220 @default.
• W3148400014 hasConcept C127413603 @default.
• W3148400014 hasConcept C138885662 @default.
• W3148400014 hasConcept C139807058 @default.
• W3148400014 hasConcept C154945302 @default.
• W3148400014 hasConcept C159886148 @default.
• W3148400014 hasConcept C165064840 @default.
• W3148400014 hasConcept C2524010 @default.
• W3148400014 hasConcept C28719098 @default.
• W3148400014 hasConcept C33923547 @default.
• W3148400014 hasConcept C41008148 @default.
• W3148400014 hasConcept C41895202 @default.
• W3148400014 hasConcept C42475967 @default.
• W3148400014 hasConcept C7149132 @default.
• W3148400014 hasConcept C97541855 @default.
• W3148400014 hasConceptScore W3148400014C105795698 @default.
• W3148400014 hasConceptScore W3148400014C106189395 @default.
• W3148400014 hasConceptScore W3148400014C120665830 @default.
• W3148400014 hasConceptScore W3148400014C121332964 @default.
• W3148400014 hasConceptScore W3148400014C126255220 @default.
• W3148400014 hasConceptScore W3148400014C127413603 @default.
• W3148400014 hasConceptScore W3148400014C138885662 @default.
• W3148400014 hasConceptScore W3148400014C139807058 @default.
• W3148400014 hasConceptScore W3148400014C154945302 @default.
• W3148400014 hasConceptScore W3148400014C159886148 @default.
• W3148400014 hasConceptScore W3148400014C165064840 @default.
• W3148400014 hasConceptScore W3148400014C2524010 @default.
• W3148400014 hasConceptScore W3148400014C28719098 @default.
• W3148400014 hasConceptScore W3148400014C33923547 @default.
• W3148400014 hasConceptScore W3148400014C41008148 @default.
• W3148400014 hasConceptScore W3148400014C41895202 @default.
• W3148400014 hasConceptScore W3148400014C42475967 @default.
• W3148400014 hasConceptScore W3148400014C7149132 @default.
• W3148400014 hasConceptScore W3148400014C97541855 @default.
• W3148400014 hasLocation W31484000141 @default.
• W3148400014 hasOpenAccess W3148400014 @default.
• W3148400014 hasPrimaryLocation W31484000141 @default.
• W3148400014 hasRelatedWork W2806789469 @default.
• W3148400014 hasRelatedWork W2955180297 @default.

• next