Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902806543> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2902806543 abstract "To overcome the curse of dimensionality and curse of modeling in Dynamic Programming (DP) methods for solving classical Markov Decision Process (MDP) problems, Reinforcement Learning (RL) algorithms are popular. In this paper, we consider an infinite-horizon average reward MDP problem and prove the optimality of the threshold policy under certain conditions. Traditional RL techniques do not exploit the threshold nature of optimal policy while learning. We propose a new RL algorithm which utilizes the known threshold structure of the optimal policy while learning by reducing the feasible policy space. We establish that the proposed algorithm converges to the optimal policy. It provides a significant improvement in convergence speed and computational and storage complexity over traditional RL algorithms. The proposed technique can be applied to a wide variety of optimization problems that include energy efficient data transmission and management of queues. We exhibit the improvement in convergence speed of the proposed algorithm over other RL algorithms through simulations." @default.
- W2902806543 created "2018-12-11" @default.
- W2902806543 creator A5018541798 @default.
- W2902806543 creator A5018587336 @default.
- W2902806543 creator A5018946124 @default.
- W2902806543 creator A5034853149 @default.
- W2902806543 date "2019-03-12" @default.
- W2902806543 modified "2023-09-24" @default.
- W2902806543 title "A Structure-aware Online Learning Algorithm for Markov Decision Processes" @default.
- W2902806543 cites W1500945877 @default.
- W2902806543 cites W1980922866 @default.
- W2902806543 cites W2021441076 @default.
- W2902806543 cites W2070570138 @default.
- W2902806543 cites W2071983464 @default.
- W2902806543 cites W2082261506 @default.
- W2902806543 cites W2102195169 @default.
- W2902806543 cites W2120465407 @default.
- W2902806543 cites W2124715093 @default.
- W2902806543 cites W2138410336 @default.
- W2902806543 cites W2138717292 @default.
- W2902806543 cites W2154204727 @default.
- W2902806543 cites W2167641136 @default.
- W2902806543 cites W2487144912 @default.
- W2902806543 cites W2791825310 @default.
- W2902806543 cites W2964273152 @default.
- W2902806543 cites W4214717370 @default.
- W2902806543 doi "https://doi.org/10.1145/3306309.3306321" @default.
- W2902806543 hasPublicationYear "2019" @default.
- W2902806543 type Work @default.
- W2902806543 sameAs 2902806543 @default.
- W2902806543 citedByCount "4" @default.
- W2902806543 countsByYear W29028065432019 @default.
- W2902806543 countsByYear W29028065432022 @default.
- W2902806543 crossrefType "proceedings-article" @default.
- W2902806543 hasAuthorship W2902806543A5018541798 @default.
- W2902806543 hasAuthorship W2902806543A5018587336 @default.
- W2902806543 hasAuthorship W2902806543A5018946124 @default.
- W2902806543 hasAuthorship W2902806543A5034853149 @default.
- W2902806543 hasBestOaLocation W29028065432 @default.
- W2902806543 hasConcept C105795698 @default.
- W2902806543 hasConcept C106189395 @default.
- W2902806543 hasConcept C119857082 @default.
- W2902806543 hasConcept C154945302 @default.
- W2902806543 hasConcept C159886148 @default.
- W2902806543 hasConcept C33923547 @default.
- W2902806543 hasConcept C41008148 @default.
- W2902806543 hasConcept C98763669 @default.
- W2902806543 hasConceptScore W2902806543C105795698 @default.
- W2902806543 hasConceptScore W2902806543C106189395 @default.
- W2902806543 hasConceptScore W2902806543C119857082 @default.
- W2902806543 hasConceptScore W2902806543C154945302 @default.
- W2902806543 hasConceptScore W2902806543C159886148 @default.
- W2902806543 hasConceptScore W2902806543C33923547 @default.
- W2902806543 hasConceptScore W2902806543C41008148 @default.
- W2902806543 hasConceptScore W2902806543C98763669 @default.
- W2902806543 hasFunder F4320321071 @default.
- W2902806543 hasLocation W29028065431 @default.
- W2902806543 hasLocation W29028065432 @default.
- W2902806543 hasOpenAccess W2902806543 @default.
- W2902806543 hasPrimaryLocation W29028065431 @default.
- W2902806543 hasRelatedWork W1970298188 @default.
- W2902806543 hasRelatedWork W2016503522 @default.
- W2902806543 hasRelatedWork W2026691440 @default.
- W2902806543 hasRelatedWork W2029936267 @default.
- W2902806543 hasRelatedWork W2068961128 @default.
- W2902806543 hasRelatedWork W2104198943 @default.
- W2902806543 hasRelatedWork W2117282672 @default.
- W2902806543 hasRelatedWork W2985981384 @default.
- W2902806543 hasRelatedWork W3148706714 @default.
- W2902806543 hasRelatedWork W2113324011 @default.
- W2902806543 isParatext "false" @default.
- W2902806543 isRetracted "false" @default.
- W2902806543 magId "2902806543" @default.
- W2902806543 workType "article" @default.