Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892053860> ?p ?o ?g. }
- W2892053860 abstract "Reinforcement learning (RL) is a suitable approach for controlling systems with unknown or time-varying dynamics. RL in principle does not require a model of the system, but before it learns an acceptable policy, it needs many unsuccessful trials, which real robots usually cannot withstand. It is well known that RL can be sped up and made safer by using models learned online. In this paper, we propose to use symbolic regression to construct compact, parsimonious models described by analytic equations, which are suitable for realtime robot control. Single node genetic programming (SNGP) is employed as a tool to automatically search for equations fitting the available data. We demonstrate the approach on two benchmark examples: a simulated mobile robot and the pendulum swing-up problem; the latter both in simulations and real-time experiments. The results show that through this approach we can find accurate models even for small batches of training data. Based on the symbolic model found, RL can control the system well." @default.
- W2892053860 created "2018-09-27" @default.
- W2892053860 creator A5004892921 @default.
- W2892053860 creator A5033348430 @default.
- W2892053860 creator A5084264842 @default.
- W2892053860 date "2018-05-01" @default.
- W2892053860 modified "2023-09-30" @default.
- W2892053860 title "Data-driven Construction of Symbolic Process Models for Reinforcement Learning" @default.
- W2892053860 cites W1689445748 @default.
- W2892053860 cites W1949804828 @default.
- W2892053860 cites W1966086707 @default.
- W2892053860 cites W1979769287 @default.
- W2892053860 cites W1980035368 @default.
- W2892053860 cites W199153045 @default.
- W2892053860 cites W1996928089 @default.
- W2892053860 cites W2001095967 @default.
- W2892053860 cites W2046633936 @default.
- W2892053860 cites W2056624909 @default.
- W2892053860 cites W2068823081 @default.
- W2892053860 cites W2103263764 @default.
- W2892053860 cites W2127107099 @default.
- W2892053860 cites W2289849244 @default.
- W2892053860 cites W2408978589 @default.
- W2892053860 cites W2509705549 @default.
- W2892053860 cites W2547065907 @default.
- W2892053860 cites W2570076534 @default.
- W2892053860 cites W2735901402 @default.
- W2892053860 cites W2766046980 @default.
- W2892053860 cites W2769736739 @default.
- W2892053860 cites W326419249 @default.
- W2892053860 cites W4211089519 @default.
- W2892053860 doi "https://doi.org/10.1109/icra.2018.8461182" @default.
- W2892053860 hasPublicationYear "2018" @default.
- W2892053860 type Work @default.
- W2892053860 sameAs 2892053860 @default.
- W2892053860 citedByCount "7" @default.
- W2892053860 countsByYear W28920538602018 @default.
- W2892053860 countsByYear W28920538602019 @default.
- W2892053860 countsByYear W28920538602020 @default.
- W2892053860 countsByYear W28920538602021 @default.
- W2892053860 countsByYear W28920538602023 @default.
- W2892053860 crossrefType "proceedings-article" @default.
- W2892053860 hasAuthorship W2892053860A5004892921 @default.
- W2892053860 hasAuthorship W2892053860A5033348430 @default.
- W2892053860 hasAuthorship W2892053860A5084264842 @default.
- W2892053860 hasConcept C110332635 @default.
- W2892053860 hasConcept C111919701 @default.
- W2892053860 hasConcept C119857082 @default.
- W2892053860 hasConcept C121332964 @default.
- W2892053860 hasConcept C13280743 @default.
- W2892053860 hasConcept C154945302 @default.
- W2892053860 hasConcept C158622935 @default.
- W2892053860 hasConcept C167183279 @default.
- W2892053860 hasConcept C185798385 @default.
- W2892053860 hasConcept C192921069 @default.
- W2892053860 hasConcept C199360897 @default.
- W2892053860 hasConcept C19966478 @default.
- W2892053860 hasConcept C205649164 @default.
- W2892053860 hasConcept C2776400721 @default.
- W2892053860 hasConcept C2776654903 @default.
- W2892053860 hasConcept C2780801425 @default.
- W2892053860 hasConcept C38652104 @default.
- W2892053860 hasConcept C41008148 @default.
- W2892053860 hasConcept C62520636 @default.
- W2892053860 hasConcept C90509273 @default.
- W2892053860 hasConcept C97541855 @default.
- W2892053860 hasConcept C98045186 @default.
- W2892053860 hasConceptScore W2892053860C110332635 @default.
- W2892053860 hasConceptScore W2892053860C111919701 @default.
- W2892053860 hasConceptScore W2892053860C119857082 @default.
- W2892053860 hasConceptScore W2892053860C121332964 @default.
- W2892053860 hasConceptScore W2892053860C13280743 @default.
- W2892053860 hasConceptScore W2892053860C154945302 @default.
- W2892053860 hasConceptScore W2892053860C158622935 @default.
- W2892053860 hasConceptScore W2892053860C167183279 @default.
- W2892053860 hasConceptScore W2892053860C185798385 @default.
- W2892053860 hasConceptScore W2892053860C192921069 @default.
- W2892053860 hasConceptScore W2892053860C199360897 @default.
- W2892053860 hasConceptScore W2892053860C19966478 @default.
- W2892053860 hasConceptScore W2892053860C205649164 @default.
- W2892053860 hasConceptScore W2892053860C2776400721 @default.
- W2892053860 hasConceptScore W2892053860C2776654903 @default.
- W2892053860 hasConceptScore W2892053860C2780801425 @default.
- W2892053860 hasConceptScore W2892053860C38652104 @default.
- W2892053860 hasConceptScore W2892053860C41008148 @default.
- W2892053860 hasConceptScore W2892053860C62520636 @default.
- W2892053860 hasConceptScore W2892053860C90509273 @default.
- W2892053860 hasConceptScore W2892053860C97541855 @default.
- W2892053860 hasConceptScore W2892053860C98045186 @default.
- W2892053860 hasLocation W28920538601 @default.
- W2892053860 hasOpenAccess W2892053860 @default.
- W2892053860 hasPrimaryLocation W28920538601 @default.
- W2892053860 hasRelatedWork W2067349577 @default.
- W2892053860 hasRelatedWork W2246414475 @default.
- W2892053860 hasRelatedWork W2771145196 @default.
- W2892053860 hasRelatedWork W2907103250 @default.
- W2892053860 hasRelatedWork W2964855005 @default.
- W2892053860 hasRelatedWork W2977089467 @default.
- W2892053860 hasRelatedWork W3098038161 @default.
- W2892053860 hasRelatedWork W3200734637 @default.