Matches in SemOpenAlex for { <https://semopenalex.org/work/W2813777834> ?p ?o ?g. }
- W2813777834 abstract "The present work extends the randomized shortest-paths framework (RSP), interpolating between shortest-path and random-walk routing in a network, in three directions. First, it shows how to deal with equality constraints on a subset of transition probabilities and develops a generic algorithm for solving this constrained RSP problem using Lagrangian duality. Second, it derives a surprisingly simple iterative procedure to compute the optimal, randomized, routing policy generalizing the previously developed soft Bellman-Ford algorithm. The resulting algorithm allows balancing exploitation and exploration in an optimal way by interpolating between a pure random behavior and the deterministic, optimal, policy (least-cost paths) while satisfying the constraints. Finally, the two algorithms are applied to Markov decision problems by considering the process as a constrained RSP on a bipartite state-action graph. In this context, the derived soft value iteration algorithm appears to be closely related to dynamic policy programming as well as Kullback-Leibler and path integral control, and similar to a recently introduced reinforcement learning exploration strategy. This shows that this strategy is optimal in the RSP sense - it minimizes expected path cost subject to relative entropy constraint. Simulation results on illustrative examples show that the model behaves as expected." @default.
- W2813777834 created "2018-07-19" @default.
- W2813777834 creator A5001517214 @default.
- W2813777834 creator A5015460788 @default.
- W2813777834 creator A5035524518 @default.
- W2813777834 creator A5082953614 @default.
- W2813777834 date "2018-07-01" @default.
- W2813777834 modified "2023-09-27" @default.
- W2813777834 title "A Constrained Randomized Shortest-Paths Framework for Optimal Exploration" @default.
- W2813777834 cites W1479694349 @default.
- W2813777834 cites W1487444668 @default.
- W2813777834 cites W1497576442 @default.
- W2813777834 cites W1503398984 @default.
- W2813777834 cites W1542941925 @default.
- W2813777834 cites W1559582792 @default.
- W2813777834 cites W1576452626 @default.
- W2813777834 cites W1689629105 @default.
- W2813777834 cites W1777267699 @default.
- W2813777834 cites W1966514629 @default.
- W2813777834 cites W1972636593 @default.
- W2813777834 cites W1973948212 @default.
- W2813777834 cites W1976918195 @default.
- W2813777834 cites W1977545325 @default.
- W2813777834 cites W1978942630 @default.
- W2813777834 cites W2012796346 @default.
- W2813777834 cites W2032558547 @default.
- W2813777834 cites W2034921015 @default.
- W2813777834 cites W2042708996 @default.
- W2813777834 cites W2051228781 @default.
- W2813777834 cites W2058068872 @default.
- W2813777834 cites W2065229575 @default.
- W2813777834 cites W2075379212 @default.
- W2813777834 cites W2092543186 @default.
- W2813777834 cites W2098432798 @default.
- W2813777834 cites W2107662876 @default.
- W2813777834 cites W2115809996 @default.
- W2813777834 cites W2119567691 @default.
- W2813777834 cites W2122597713 @default.
- W2813777834 cites W2130179125 @default.
- W2813777834 cites W2133161531 @default.
- W2813777834 cites W2134640096 @default.
- W2813777834 cites W2145060720 @default.
- W2813777834 cites W2161813919 @default.
- W2813777834 cites W2161984370 @default.
- W2813777834 cites W2169847772 @default.
- W2813777834 cites W2209229337 @default.
- W2813777834 cites W2279353332 @default.
- W2813777834 cites W2295428206 @default.
- W2813777834 cites W2296319761 @default.
- W2813777834 cites W2341059552 @default.
- W2813777834 cites W2497633600 @default.
- W2813777834 cites W2619268125 @default.
- W2813777834 cites W2751555667 @default.
- W2813777834 cites W2797302609 @default.
- W2813777834 cites W2797925981 @default.
- W2813777834 cites W2952474493 @default.
- W2813777834 cites W2962901215 @default.
- W2813777834 cites W2963169817 @default.
- W2813777834 cites W2987280934 @default.
- W2813777834 cites W48257500 @default.
- W2813777834 cites W53596869 @default.
- W2813777834 cites W592715486 @default.
- W2813777834 cites W657245069 @default.
- W2813777834 hasPublicationYear "2018" @default.
- W2813777834 type Work @default.
- W2813777834 sameAs 2813777834 @default.
- W2813777834 citedByCount "5" @default.
- W2813777834 countsByYear W28137778342018 @default.
- W2813777834 countsByYear W28137778342019 @default.
- W2813777834 countsByYear W28137778342020 @default.
- W2813777834 crossrefType "posted-content" @default.
- W2813777834 hasAuthorship W2813777834A5001517214 @default.
- W2813777834 hasAuthorship W2813777834A5015460788 @default.
- W2813777834 hasAuthorship W2813777834A5035524518 @default.
- W2813777834 hasAuthorship W2813777834A5082953614 @default.
- W2813777834 hasConcept C105795698 @default.
- W2813777834 hasConcept C106189395 @default.
- W2813777834 hasConcept C126255220 @default.
- W2813777834 hasConcept C132525143 @default.
- W2813777834 hasConcept C14646407 @default.
- W2813777834 hasConcept C159886148 @default.
- W2813777834 hasConcept C178067994 @default.
- W2813777834 hasConcept C22590252 @default.
- W2813777834 hasConcept C33923547 @default.
- W2813777834 hasConcept C37404715 @default.
- W2813777834 hasConcept C41008148 @default.
- W2813777834 hasConcept C70266271 @default.
- W2813777834 hasConcept C80444323 @default.
- W2813777834 hasConceptScore W2813777834C105795698 @default.
- W2813777834 hasConceptScore W2813777834C106189395 @default.
- W2813777834 hasConceptScore W2813777834C126255220 @default.
- W2813777834 hasConceptScore W2813777834C132525143 @default.
- W2813777834 hasConceptScore W2813777834C14646407 @default.
- W2813777834 hasConceptScore W2813777834C159886148 @default.
- W2813777834 hasConceptScore W2813777834C178067994 @default.
- W2813777834 hasConceptScore W2813777834C22590252 @default.
- W2813777834 hasConceptScore W2813777834C33923547 @default.
- W2813777834 hasConceptScore W2813777834C37404715 @default.
- W2813777834 hasConceptScore W2813777834C41008148 @default.
- W2813777834 hasConceptScore W2813777834C70266271 @default.