Matches in SemOpenAlex for { <https://semopenalex.org/work/W158410110> ?p ?o ?g. }
Showing items 1 to 47 of
47
with 100 items per page.
- W158410110 endingPage "127" @default.
- W158410110 startingPage "117" @default.
- W158410110 abstract "Presented topic is from the research field called Artificial Life, but contributes also to the field of Artificial Intelligence (AI), Robotics and potentially into many other aspects of research. In this paper, there is reviewed and tested new approach to autonomous design of agent architectures. This novel approach is inspired by inherited modularity of biological brains. During designing of new brains, the evolution is not directly connecting individual neurons. Rather than that, it composes new brains by connecting larger, widely reused areas (modules). In this approach, agent architectures are represented as hybrid artificial neural networks composed of heterogeneous modules. Each module can implement different selected algorithm. Rather than describing this framework, this paper focuses on designing of one module. Such a module represents one component of hybrid neural network and can seamlessly integrate a selected algorithm into the node. The course of design of such a module is described on example of discrete reinforcement learning algorithm. The requirements posed by the framework are presented, the modifications on the classical version of algorithm are mentioned and then the resulting performance of module with expectations is evaluated. Finally, the future use cases of this module are described." @default.
- W158410110 created "2016-06-24" @default.
- W158410110 creator A5053986921 @default.
- W158410110 creator A5058831673 @default.
- W158410110 date "2014-01-01" @default.
- W158410110 modified "2023-09-26" @default.
- W158410110 title "Q-Learning Algorithm Module in Hybrid Artificial Neural Network Systems" @default.
- W158410110 cites W1481164811 @default.
- W158410110 cites W1999925021 @default.
- W158410110 cites W2045257906 @default.
- W158410110 cites W2117502083 @default.
- W158410110 cites W2164653071 @default.
- W158410110 cites W2170942403 @default.
- W158410110 cites W2006370340 @default.
- W158410110 doi "https://doi.org/10.1007/978-3-319-06740-7_11" @default.
- W158410110 hasPublicationYear "2014" @default.
- W158410110 type Work @default.
- W158410110 sameAs 158410110 @default.
- W158410110 citedByCount "0" @default.
- W158410110 crossrefType "book-chapter" @default.
- W158410110 hasAuthorship W158410110A5053986921 @default.
- W158410110 hasAuthorship W158410110A5058831673 @default.
- W158410110 hasConcept C154945302 @default.
- W158410110 hasConcept C41008148 @default.
- W158410110 hasConcept C50644808 @default.
- W158410110 hasConceptScore W158410110C154945302 @default.
- W158410110 hasConceptScore W158410110C41008148 @default.
- W158410110 hasConceptScore W158410110C50644808 @default.
- W158410110 hasLocation W1584101101 @default.
- W158410110 hasOpenAccess W158410110 @default.
- W158410110 hasPrimaryLocation W1584101101 @default.
- W158410110 hasRelatedWork W2159443810 @default.
- W158410110 hasRelatedWork W2358668433 @default.
- W158410110 hasRelatedWork W2386387936 @default.
- W158410110 hasRelatedWork W2390279801 @default.
- W158410110 hasRelatedWork W2748952813 @default.
- W158410110 hasRelatedWork W2899084033 @default.
- W158410110 hasRelatedWork W3001020386 @default.
- W158410110 hasRelatedWork W3107474891 @default.
- W158410110 hasRelatedWork W644753246 @default.
- W158410110 hasRelatedWork W1629725936 @default.
- W158410110 isParatext "false" @default.
- W158410110 isRetracted "false" @default.
- W158410110 magId "158410110" @default.
- W158410110 workType "book-chapter" @default.