Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896721375> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2896721375 abstract "The article deals with the solution of game problems by the example of finding a path in a labyrinth with the help of a neural network. Such a task can be solved by one of the existing methods of training with confirmation, but the solutions have several drawbacks, which include, for example, a long learning time for the classical training method with confirmation. Analysis of these algorithms is presented, including a training method with confirmation based on Monte Carlo search method in the game tree. There has been described a variant of setting the initial problem, in which the input consisting of only one value - the sign indicating that the previous step was successful or deadlock - is delivered to the neural network, instead of the entire field of the labyrinth. A variant of solving the problem is posed by the synthesis of a neural network based on a preliminary synthesized algorithm. A neural network obtained is constructed from an informal description of the algorithm; it allows searching for a path in the labyrinth. The main idea used in the formation of a neural network is that the detected or explored path is marked in the neural network by the weights of the units, the dead-end path - by the negative weights, and the unexplored path - by the zero weights. When a robot occurs in a dead end, the process of finding the path is restarted from the initial state, and the dead end state is marked in the labyrinth as unattainable. Several stages of the path search process in the labyrinth illustrating the operation of the synthesized neural network are presented. There has been given a comparative analysis of the solution obtained and of the existing methods of training with confirmation." @default.
- W2896721375 created "2018-10-26" @default.
- W2896721375 creator A5047859171 @default.
- W2896721375 creator A5073048826 @default.
- W2896721375 date "2018-10-25" @default.
- W2896721375 modified "2023-09-28" @default.
- W2896721375 title "USING NEURAL NETWORKS FOR SOLVING GAME TASKS ON THE EXAMPLE OF THE PROBLEM OF SEARCHING THE WAY IN THE LABYRINTH" @default.
- W2896721375 cites W2609860019 @default.
- W2896721375 doi "https://doi.org/10.24143/2072-9502-2018-4-33-42" @default.
- W2896721375 hasPublicationYear "2018" @default.
- W2896721375 type Work @default.
- W2896721375 sameAs 2896721375 @default.
- W2896721375 citedByCount "0" @default.
- W2896721375 crossrefType "journal-article" @default.
- W2896721375 hasAuthorship W2896721375A5047859171 @default.
- W2896721375 hasAuthorship W2896721375A5073048826 @default.
- W2896721375 hasBestOaLocation W28967213751 @default.
- W2896721375 hasConcept C105795698 @default.
- W2896721375 hasConcept C111919701 @default.
- W2896721375 hasConcept C11413529 @default.
- W2896721375 hasConcept C120314980 @default.
- W2896721375 hasConcept C134306372 @default.
- W2896721375 hasConcept C139676723 @default.
- W2896721375 hasConcept C147168706 @default.
- W2896721375 hasConcept C154945302 @default.
- W2896721375 hasConcept C159023740 @default.
- W2896721375 hasConcept C19499675 @default.
- W2896721375 hasConcept C199360897 @default.
- W2896721375 hasConcept C2777735758 @default.
- W2896721375 hasConcept C33923547 @default.
- W2896721375 hasConcept C41008148 @default.
- W2896721375 hasConcept C46149586 @default.
- W2896721375 hasConcept C48103436 @default.
- W2896721375 hasConcept C50644808 @default.
- W2896721375 hasConcept C98045186 @default.
- W2896721375 hasConceptScore W2896721375C105795698 @default.
- W2896721375 hasConceptScore W2896721375C111919701 @default.
- W2896721375 hasConceptScore W2896721375C11413529 @default.
- W2896721375 hasConceptScore W2896721375C120314980 @default.
- W2896721375 hasConceptScore W2896721375C134306372 @default.
- W2896721375 hasConceptScore W2896721375C139676723 @default.
- W2896721375 hasConceptScore W2896721375C147168706 @default.
- W2896721375 hasConceptScore W2896721375C154945302 @default.
- W2896721375 hasConceptScore W2896721375C159023740 @default.
- W2896721375 hasConceptScore W2896721375C19499675 @default.
- W2896721375 hasConceptScore W2896721375C199360897 @default.
- W2896721375 hasConceptScore W2896721375C2777735758 @default.
- W2896721375 hasConceptScore W2896721375C33923547 @default.
- W2896721375 hasConceptScore W2896721375C41008148 @default.
- W2896721375 hasConceptScore W2896721375C46149586 @default.
- W2896721375 hasConceptScore W2896721375C48103436 @default.
- W2896721375 hasConceptScore W2896721375C50644808 @default.
- W2896721375 hasConceptScore W2896721375C98045186 @default.
- W2896721375 hasLocation W28967213751 @default.
- W2896721375 hasOpenAccess W2896721375 @default.
- W2896721375 hasPrimaryLocation W28967213751 @default.
- W2896721375 hasRelatedWork W1539123944 @default.
- W2896721375 hasRelatedWork W1544441750 @default.
- W2896721375 hasRelatedWork W2003908543 @default.
- W2896721375 hasRelatedWork W2009559981 @default.
- W2896721375 hasRelatedWork W2065856308 @default.
- W2896721375 hasRelatedWork W2279054051 @default.
- W2896721375 hasRelatedWork W2314328290 @default.
- W2896721375 hasRelatedWork W2366822267 @default.
- W2896721375 hasRelatedWork W2386387936 @default.
- W2896721375 hasRelatedWork W2748952813 @default.
- W2896721375 isParatext "false" @default.
- W2896721375 isRetracted "false" @default.
- W2896721375 magId "2896721375" @default.
- W2896721375 workType "article" @default.