Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308616306> ?p ?o ?g. }
- W4308616306 endingPage "2378" @default.
- W4308616306 startingPage "2361" @default.
- W4308616306 abstract "In this paper, a model-free off-policy reinforcement learning (RL) algorithm is proposed to address the optimal tracking control (OTC) problem for discrete-time Markov jump linear systems (MJLSs). The tracking reference signal is firstly augmented into discrete-time MJLSs, whereby the original tracking control problem is converted to the optimal control problem of the augmented system. The corresponding augmented coupled game algebraic Riccati equation (ACGARE) is then derived. On this basis, an online RL algorithm is developed to solve the OTC problem by using the policy iteration (PI) technique. Then, a novel model-free method is proposed, which eliminates the requirement of the system dynamics and transition probability. Finally, a simulation example is provided to prove the convergence and validate the effectiveness of the proposed algorithm." @default.
- W4308616306 created "2022-11-13" @default.
- W4308616306 creator A5001371746 @default.
- W4308616306 creator A5009768180 @default.
- W4308616306 creator A5066599847 @default.
- W4308616306 creator A5078975428 @default.
- W4308616306 creator A5079133090 @default.
- W4308616306 creator A5085136761 @default.
- W4308616306 creator A5085669742 @default.
- W4308616306 date "2023-02-01" @default.
- W4308616306 modified "2023-10-18" @default.
- W4308616306 title "Off-policy reinforcement learning for tracking control of discrete-time Markov jump linear systems with completely unknown dynamics" @default.
- W4308616306 cites W1529494582 @default.
- W4308616306 cites W1967793246 @default.
- W4308616306 cites W1968908471 @default.
- W4308616306 cites W1969959431 @default.
- W4308616306 cites W1990463984 @default.
- W4308616306 cites W1999213690 @default.
- W4308616306 cites W2003183707 @default.
- W4308616306 cites W2024303516 @default.
- W4308616306 cites W2048687352 @default.
- W4308616306 cites W2052305027 @default.
- W4308616306 cites W2053695185 @default.
- W4308616306 cites W2060605484 @default.
- W4308616306 cites W2061280864 @default.
- W4308616306 cites W2098035803 @default.
- W4308616306 cites W2125944702 @default.
- W4308616306 cites W2148439597 @default.
- W4308616306 cites W2152161277 @default.
- W4308616306 cites W2286604276 @default.
- W4308616306 cites W2527569699 @default.
- W4308616306 cites W2580629550 @default.
- W4308616306 cites W2725661304 @default.
- W4308616306 cites W2752857562 @default.
- W4308616306 cites W2774042190 @default.
- W4308616306 cites W2790265915 @default.
- W4308616306 cites W2809121899 @default.
- W4308616306 cites W2809310269 @default.
- W4308616306 cites W2914172002 @default.
- W4308616306 cites W2943141190 @default.
- W4308616306 cites W2943276199 @default.
- W4308616306 cites W2947048520 @default.
- W4308616306 cites W2964200294 @default.
- W4308616306 cites W2979865550 @default.
- W4308616306 cites W3016467967 @default.
- W4308616306 cites W3045566279 @default.
- W4308616306 cites W3106074051 @default.
- W4308616306 cites W3211213622 @default.
- W4308616306 cites W4285116599 @default.
- W4308616306 cites W4285281034 @default.
- W4308616306 cites W4291270709 @default.
- W4308616306 doi "https://doi.org/10.1016/j.jfranklin.2022.10.052" @default.
- W4308616306 hasPublicationYear "2023" @default.
- W4308616306 type Work @default.
- W4308616306 citedByCount "0" @default.
- W4308616306 crossrefType "journal-article" @default.
- W4308616306 hasAuthorship W4308616306A5001371746 @default.
- W4308616306 hasAuthorship W4308616306A5009768180 @default.
- W4308616306 hasAuthorship W4308616306A5066599847 @default.
- W4308616306 hasAuthorship W4308616306A5078975428 @default.
- W4308616306 hasAuthorship W4308616306A5079133090 @default.
- W4308616306 hasAuthorship W4308616306A5085136761 @default.
- W4308616306 hasAuthorship W4308616306A5085669742 @default.
- W4308616306 hasConcept C105795698 @default.
- W4308616306 hasConcept C106189395 @default.
- W4308616306 hasConcept C117619785 @default.
- W4308616306 hasConcept C119857082 @default.
- W4308616306 hasConcept C121332964 @default.
- W4308616306 hasConcept C12426560 @default.
- W4308616306 hasConcept C126255220 @default.
- W4308616306 hasConcept C134306372 @default.
- W4308616306 hasConcept C13847129 @default.
- W4308616306 hasConcept C154945302 @default.
- W4308616306 hasConcept C15744967 @default.
- W4308616306 hasConcept C159886148 @default.
- W4308616306 hasConcept C162324750 @default.
- W4308616306 hasConcept C19417346 @default.
- W4308616306 hasConcept C203479927 @default.
- W4308616306 hasConcept C2524010 @default.
- W4308616306 hasConcept C2775924081 @default.
- W4308616306 hasConcept C2775936607 @default.
- W4308616306 hasConcept C2777303404 @default.
- W4308616306 hasConcept C2780695682 @default.
- W4308616306 hasConcept C33923547 @default.
- W4308616306 hasConcept C41008148 @default.
- W4308616306 hasConcept C45473103 @default.
- W4308616306 hasConcept C47446073 @default.
- W4308616306 hasConcept C50522688 @default.
- W4308616306 hasConcept C55689738 @default.
- W4308616306 hasConcept C62520636 @default.
- W4308616306 hasConcept C6557445 @default.
- W4308616306 hasConcept C78045399 @default.
- W4308616306 hasConcept C86803240 @default.
- W4308616306 hasConcept C91575142 @default.
- W4308616306 hasConcept C9376300 @default.
- W4308616306 hasConcept C97541855 @default.
- W4308616306 hasConcept C98763669 @default.
- W4308616306 hasConceptScore W4308616306C105795698 @default.