Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044916305> ?p ?o ?g. }
- W3044916305 endingPage "753" @default.
- W3044916305 startingPage "741" @default.
- W3044916305 abstract "Abstract Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability." @default.
- W3044916305 created "2020-07-29" @default.
- W3044916305 creator A5049949859 @default.
- W3044916305 creator A5050248676 @default.
- W3044916305 creator A5083092570 @default.
- W3044916305 date "2020-07-25" @default.
- W3044916305 modified "2023-10-06" @default.
- W3044916305 title "Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis" @default.
- W3044916305 cites W1481961312 @default.
- W3044916305 cites W1599449370 @default.
- W3044916305 cites W1831373594 @default.
- W3044916305 cites W1991542861 @default.
- W3044916305 cites W2121162457 @default.
- W3044916305 cites W2124847822 @default.
- W3044916305 cites W2145339207 @default.
- W3044916305 cites W2166219119 @default.
- W3044916305 cites W2509705549 @default.
- W3044916305 cites W2570076534 @default.
- W3044916305 cites W2590959390 @default.
- W3044916305 cites W2735328866 @default.
- W3044916305 cites W2746553466 @default.
- W3044916305 cites W2760661167 @default.
- W3044916305 cites W2766447205 @default.
- W3044916305 cites W2783396564 @default.
- W3044916305 cites W2892053860 @default.
- W3044916305 cites W2909661184 @default.
- W3044916305 cites W2913240367 @default.
- W3044916305 cites W2934819789 @default.
- W3044916305 cites W2944781902 @default.
- W3044916305 cites W2945976633 @default.
- W3044916305 cites W2963672746 @default.
- W3044916305 cites W2973449430 @default.
- W3044916305 doi "https://doi.org/10.1007/s40747-020-00175-y" @default.
- W3044916305 hasPublicationYear "2020" @default.
- W3044916305 type Work @default.
- W3044916305 sameAs 3044916305 @default.
- W3044916305 citedByCount "8" @default.
- W3044916305 countsByYear W30449163052020 @default.
- W3044916305 countsByYear W30449163052021 @default.
- W3044916305 countsByYear W30449163052022 @default.
- W3044916305 countsByYear W30449163052023 @default.
- W3044916305 crossrefType "journal-article" @default.
- W3044916305 hasAuthorship W3044916305A5049949859 @default.
- W3044916305 hasAuthorship W3044916305A5050248676 @default.
- W3044916305 hasAuthorship W3044916305A5083092570 @default.
- W3044916305 hasBestOaLocation W30449163051 @default.
- W3044916305 hasConcept C110332635 @default.
- W3044916305 hasConcept C111472728 @default.
- W3044916305 hasConcept C113174947 @default.
- W3044916305 hasConcept C119857082 @default.
- W3044916305 hasConcept C121835503 @default.
- W3044916305 hasConcept C134306372 @default.
- W3044916305 hasConcept C138885662 @default.
- W3044916305 hasConcept C139502532 @default.
- W3044916305 hasConcept C154945302 @default.
- W3044916305 hasConcept C159149176 @default.
- W3044916305 hasConcept C177264268 @default.
- W3044916305 hasConcept C189950617 @default.
- W3044916305 hasConcept C199360897 @default.
- W3044916305 hasConcept C2775924081 @default.
- W3044916305 hasConcept C2776401178 @default.
- W3044916305 hasConcept C2781067378 @default.
- W3044916305 hasConcept C33923547 @default.
- W3044916305 hasConcept C41008148 @default.
- W3044916305 hasConcept C41895202 @default.
- W3044916305 hasConcept C50644808 @default.
- W3044916305 hasConcept C8880873 @default.
- W3044916305 hasConcept C94966114 @default.
- W3044916305 hasConcept C97541855 @default.
- W3044916305 hasConceptScore W3044916305C110332635 @default.
- W3044916305 hasConceptScore W3044916305C111472728 @default.
- W3044916305 hasConceptScore W3044916305C113174947 @default.
- W3044916305 hasConceptScore W3044916305C119857082 @default.
- W3044916305 hasConceptScore W3044916305C121835503 @default.
- W3044916305 hasConceptScore W3044916305C134306372 @default.
- W3044916305 hasConceptScore W3044916305C138885662 @default.
- W3044916305 hasConceptScore W3044916305C139502532 @default.
- W3044916305 hasConceptScore W3044916305C154945302 @default.
- W3044916305 hasConceptScore W3044916305C159149176 @default.
- W3044916305 hasConceptScore W3044916305C177264268 @default.
- W3044916305 hasConceptScore W3044916305C189950617 @default.
- W3044916305 hasConceptScore W3044916305C199360897 @default.
- W3044916305 hasConceptScore W3044916305C2775924081 @default.
- W3044916305 hasConceptScore W3044916305C2776401178 @default.
- W3044916305 hasConceptScore W3044916305C2781067378 @default.
- W3044916305 hasConceptScore W3044916305C33923547 @default.
- W3044916305 hasConceptScore W3044916305C41008148 @default.
- W3044916305 hasConceptScore W3044916305C41895202 @default.
- W3044916305 hasConceptScore W3044916305C50644808 @default.
- W3044916305 hasConceptScore W3044916305C8880873 @default.
- W3044916305 hasConceptScore W3044916305C94966114 @default.
- W3044916305 hasConceptScore W3044916305C97541855 @default.
- W3044916305 hasFunder F4320321001 @default.
- W3044916305 hasFunder F4320321885 @default.
- W3044916305 hasIssue "3" @default.
- W3044916305 hasLocation W30449163051 @default.
- W3044916305 hasOpenAccess W3044916305 @default.
- W3044916305 hasPrimaryLocation W30449163051 @default.