Matches in SemOpenAlex for { <https://semopenalex.org/work/W2554480306> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W2554480306 abstract "Reinforcement learning allows agents to use trial and error method to learn intelligent behaviors which like human beings. However, when the learning tasks become difficult, how to define the reward function is an imperative issue. So, inverse reinforcement learning is proposed to form the reward function that imitates the process of interaction between the expert and the environment. In this paper, an Adaboost-like inverse reinforcement learning methods is proposed. This method uses Adaboost classifier and upper confidence bounds to generate the reward function for a complex task. In the imitating process, the agent continuously compares the difference between itself and the expert, and then the difference decides a specific weight for each state through Adaboost classifier. The weight combines with state confidence by upper confidence bounds to form an approximate reward function. Finally, a simulation, maze environment is used to demonstrate that the proposed method can decrease the computation time." @default.
- W2554480306 created "2016-11-30" @default.
- W2554480306 creator A5001081733 @default.
- W2554480306 creator A5061189209 @default.
- W2554480306 creator A5075809603 @default.
- W2554480306 date "2016-07-01" @default.
- W2554480306 modified "2023-09-26" @default.
- W2554480306 title "Adaboost-like method for inverse reinforcement learning" @default.
- W2554480306 cites W1999874108 @default.
- W2554480306 cites W2065041047 @default.
- W2554480306 cites W2105156548 @default.
- W2554480306 cites W2144059919 @default.
- W2554480306 doi "https://doi.org/10.1109/fuzz-ieee.2016.7737926" @default.
- W2554480306 hasPublicationYear "2016" @default.
- W2554480306 type Work @default.
- W2554480306 sameAs 2554480306 @default.
- W2554480306 citedByCount "2" @default.
- W2554480306 countsByYear W25544803062018 @default.
- W2554480306 countsByYear W25544803062023 @default.
- W2554480306 crossrefType "proceedings-article" @default.
- W2554480306 hasAuthorship W2554480306A5001081733 @default.
- W2554480306 hasAuthorship W2554480306A5061189209 @default.
- W2554480306 hasAuthorship W2554480306A5075809603 @default.
- W2554480306 hasConcept C119857082 @default.
- W2554480306 hasConcept C141404830 @default.
- W2554480306 hasConcept C154945302 @default.
- W2554480306 hasConcept C196340769 @default.
- W2554480306 hasConcept C199190896 @default.
- W2554480306 hasConcept C41008148 @default.
- W2554480306 hasConcept C95623464 @default.
- W2554480306 hasConcept C97541855 @default.
- W2554480306 hasConceptScore W2554480306C119857082 @default.
- W2554480306 hasConceptScore W2554480306C141404830 @default.
- W2554480306 hasConceptScore W2554480306C154945302 @default.
- W2554480306 hasConceptScore W2554480306C196340769 @default.
- W2554480306 hasConceptScore W2554480306C199190896 @default.
- W2554480306 hasConceptScore W2554480306C41008148 @default.
- W2554480306 hasConceptScore W2554480306C95623464 @default.
- W2554480306 hasConceptScore W2554480306C97541855 @default.
- W2554480306 hasLocation W25544803061 @default.
- W2554480306 hasOpenAccess W2554480306 @default.
- W2554480306 hasPrimaryLocation W25544803061 @default.
- W2554480306 hasRelatedWork W1479873353 @default.
- W2554480306 hasRelatedWork W1996541855 @default.
- W2554480306 hasRelatedWork W2554480306 @default.
- W2554480306 hasRelatedWork W2961085424 @default.
- W2554480306 hasRelatedWork W3212493609 @default.
- W2554480306 hasRelatedWork W4249229055 @default.
- W2554480306 hasRelatedWork W4282839226 @default.
- W2554480306 hasRelatedWork W4285046548 @default.
- W2554480306 hasRelatedWork W4319083788 @default.
- W2554480306 hasRelatedWork W2185861556 @default.
- W2554480306 isParatext "false" @default.
- W2554480306 isRetracted "false" @default.
- W2554480306 magId "2554480306" @default.
- W2554480306 workType "article" @default.