FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080730120> ?p ?o ?g. }

• W3080730120 abstract "In Markov Decision Processes (MDPs), rewards are assigned according to a function of the last state and action. This is often limiting, when the considered domain is not naturally Markovian, but becomes so after careful engineering of extended state space. The extended states record information from the past that is sufficient to assign rewards by looking just at the last state and action. Non-Markovian Reward Decision Processes (NRMDPs) extend MDPs by allowing for non-Markovian rewards, which depend on the history of states and actions. Non-Markovian rewards can be specified in temporal logics on finite traces such as LTLf/LDLf, with the great advantage of a higher abstraction and succinctness; they can then be automatically compiled into an MDP with an extended state space. We contribute to the techniques to handle temporal rewards and to the solutions to engineer them. We first present an approach to compiling temporal rewards which merges the formula automata into a single transducer, sometimes saving up to an exponential number of states. We then define monitoring rewards, which add a further level of abstraction to temporal rewards by adopting the four-valued conditions of runtime monitoring; we argue that our compilation technique allows for an efficient handling of monitoring rewards. Finally, we discuss application to reinforcement learning." @default.
• W3080730120 created "2020-09-01" @default.
• W3080730120 creator A5013290512 @default.
• W3080730120 creator A5013963601 @default.
• W3080730120 creator A5026692089 @default.
• W3080730120 creator A5057746643 @default.
• W3080730120 creator A5082921554 @default.
• W3080730120 date "2020-07-01" @default.
• W3080730120 modified "2023-09-25" @default.
• W3080730120 title "Temporal Logic Monitoring Rewards via Transducers" @default.
• W3080730120 cites W1505515950 @default.
• W3080730120 cites W1823315334 @default.
• W3080730120 cites W1965243368 @default.
• W3080730120 cites W2009064992 @default.
• W3080730120 cites W2020617153 @default.
• W3080730120 cites W2023808162 @default.
• W3080730120 cites W2054801208 @default.
• W3080730120 cites W2075773711 @default.
• W3080730120 cites W2105590118 @default.
• W3080730120 cites W2119567691 @default.
• W3080730120 cites W2120327813 @default.
• W3080730120 cites W2121517924 @default.
• W3080730120 cites W2462906003 @default.
• W3080730120 cites W2491764833 @default.
• W3080730120 cites W2493256084 @default.
• W3080730120 cites W2553882142 @default.
• W3080730120 cites W2789027502 @default.
• W3080730120 cites W2804948070 @default.
• W3080730120 cites W2808628779 @default.
• W3080730120 cites W2914941842 @default.
• W3080730120 cites W2963575966 @default.
• W3080730120 cites W2964514675 @default.
• W3080730120 cites W2966537673 @default.
• W3080730120 cites W2970673985 @default.
• W3080730120 cites W2978598593 @default.
• W3080730120 doi "https://doi.org/10.24963/kr.2020/89" @default.
• W3080730120 hasPublicationYear "2020" @default.
• W3080730120 type Work @default.
• W3080730120 sameAs 3080730120 @default.
• W3080730120 citedByCount "8" @default.
• W3080730120 countsByYear W30807301202019 @default.
• W3080730120 countsByYear W30807301202021 @default.
• W3080730120 countsByYear W30807301202022 @default.
• W3080730120 crossrefType "proceedings-article" @default.
• W3080730120 hasAuthorship W3080730120A5013290512 @default.
• W3080730120 hasAuthorship W3080730120A5013963601 @default.
• W3080730120 hasAuthorship W3080730120A5026692089 @default.
• W3080730120 hasAuthorship W3080730120A5057746643 @default.
• W3080730120 hasAuthorship W3080730120A5082921554 @default.
• W3080730120 hasBestOaLocation W30807301201 @default.
• W3080730120 hasConcept C105795698 @default.
• W3080730120 hasConcept C106189395 @default.
• W3080730120 hasConcept C111472728 @default.
• W3080730120 hasConcept C112505250 @default.
• W3080730120 hasConcept C11413529 @default.
• W3080730120 hasConcept C121332964 @default.
• W3080730120 hasConcept C124304363 @default.
• W3080730120 hasConcept C138885662 @default.
• W3080730120 hasConcept C154945302 @default.
• W3080730120 hasConcept C159886148 @default.
• W3080730120 hasConcept C171018156 @default.
• W3080730120 hasConcept C196340769 @default.
• W3080730120 hasConcept C25016198 @default.
• W3080730120 hasConcept C2524010 @default.
• W3080730120 hasConcept C2776493592 @default.
• W3080730120 hasConcept C2780791683 @default.
• W3080730120 hasConcept C33923547 @default.
• W3080730120 hasConcept C41008148 @default.
• W3080730120 hasConcept C4777664 @default.
• W3080730120 hasConcept C48103436 @default.
• W3080730120 hasConcept C62520636 @default.
• W3080730120 hasConcept C72434380 @default.
• W3080730120 hasConcept C80444323 @default.
• W3080730120 hasConcept C97541855 @default.
• W3080730120 hasConceptScore W3080730120C105795698 @default.
• W3080730120 hasConceptScore W3080730120C106189395 @default.
• W3080730120 hasConceptScore W3080730120C111472728 @default.
• W3080730120 hasConceptScore W3080730120C112505250 @default.
• W3080730120 hasConceptScore W3080730120C11413529 @default.
• W3080730120 hasConceptScore W3080730120C121332964 @default.
• W3080730120 hasConceptScore W3080730120C124304363 @default.
• W3080730120 hasConceptScore W3080730120C138885662 @default.
• W3080730120 hasConceptScore W3080730120C154945302 @default.
• W3080730120 hasConceptScore W3080730120C159886148 @default.
• W3080730120 hasConceptScore W3080730120C171018156 @default.
• W3080730120 hasConceptScore W3080730120C196340769 @default.
• W3080730120 hasConceptScore W3080730120C25016198 @default.
• W3080730120 hasConceptScore W3080730120C2524010 @default.
• W3080730120 hasConceptScore W3080730120C2776493592 @default.
• W3080730120 hasConceptScore W3080730120C2780791683 @default.
• W3080730120 hasConceptScore W3080730120C33923547 @default.
• W3080730120 hasConceptScore W3080730120C41008148 @default.
• W3080730120 hasConceptScore W3080730120C4777664 @default.
• W3080730120 hasConceptScore W3080730120C48103436 @default.
• W3080730120 hasConceptScore W3080730120C62520636 @default.
• W3080730120 hasConceptScore W3080730120C72434380 @default.
• W3080730120 hasConceptScore W3080730120C80444323 @default.
• W3080730120 hasConceptScore W3080730120C97541855 @default.
• W3080730120 hasLocation W30807301201 @default.
• W3080730120 hasLocation W30807301202 @default.

• next