Matches in SemOpenAlex for { <https://semopenalex.org/work/W2730231097> ?p ?o ?g. }
- W2730231097 abstract "In certain optimization problems, aside from the target objective, auxiliary objectives can be used. These auxiliary objectives may be either helpful or not. Often we can not determine whether an auxiliary objective is helpful. In this work we consider the EA+RL method that dynamically chooses auxiliary objectives in random local search using reinforcement learning. This method's runtime has already been theoretically analysed on different monotonic functions, and it was shown that EA+RL can exclude harmful auxiliary objectives from consideration. EA+RL has also shown good results on different real-world problems. However, it has not been theoretically analysed whether this method can efficiently optimize non-monotonic functions using simple evolutionary algorithms and reinforcement learning agents. In this paper we consider optimization of the non-monotonic JUMP function with the EA+RL method. We use two auxiliary objectives. One of them is helpful during the first phase of optimization and another one is helpful during the last phase. On other stages they are constant, so they neither help nor slow optimization down. We show that EA+RL has at least Ω(l/n) probability of solving this problem in polynomial time using random local search, which is impossible for the conventional random local search without learning. We also propose a modification of EA+RL that is guaranteed to find the optimum." @default.
- W2730231097 created "2017-07-14" @default.
- W2730231097 creator A5043992909 @default.
- W2730231097 creator A5082239479 @default.
- W2730231097 date "2017-06-01" @default.
- W2730231097 modified "2023-09-25" @default.
- W2730231097 title "Runtime Analysis of Random Local Search on JUMP function with Reinforcement Based Selection of Auxiliary Objectives" @default.
- W2730231097 cites W100529812 @default.
- W2730231097 cites W1585711251 @default.
- W2730231097 cites W1833338034 @default.
- W2730231097 cites W2006734419 @default.
- W2730231097 cites W2019111549 @default.
- W2730231097 cites W2050439249 @default.
- W2730231097 cites W2053099640 @default.
- W2730231097 cites W2055929045 @default.
- W2730231097 cites W2062018068 @default.
- W2730231097 cites W2066124178 @default.
- W2730231097 cites W2066290587 @default.
- W2730231097 cites W2073297125 @default.
- W2730231097 cites W2095453933 @default.
- W2730231097 cites W2121863487 @default.
- W2730231097 cites W2138710575 @default.
- W2730231097 cites W2138926459 @default.
- W2730231097 cites W2147026702 @default.
- W2730231097 cites W2153475092 @default.
- W2730231097 cites W2165220807 @default.
- W2730231097 cites W2464386141 @default.
- W2730231097 cites W3122779104 @default.
- W2730231097 cites W589455649 @default.
- W2730231097 doi "https://doi.org/10.1109/cec.2017.7969567" @default.
- W2730231097 hasPublicationYear "2017" @default.
- W2730231097 type Work @default.
- W2730231097 sameAs 2730231097 @default.
- W2730231097 citedByCount "0" @default.
- W2730231097 crossrefType "proceedings-article" @default.
- W2730231097 hasAuthorship W2730231097A5043992909 @default.
- W2730231097 hasAuthorship W2730231097A5082239479 @default.
- W2730231097 hasConcept C111472728 @default.
- W2730231097 hasConcept C11413529 @default.
- W2730231097 hasConcept C121332964 @default.
- W2730231097 hasConcept C126255220 @default.
- W2730231097 hasConcept C126661757 @default.
- W2730231097 hasConcept C134306372 @default.
- W2730231097 hasConcept C135320971 @default.
- W2730231097 hasConcept C138885662 @default.
- W2730231097 hasConcept C14036430 @default.
- W2730231097 hasConcept C154945302 @default.
- W2730231097 hasConcept C2780586882 @default.
- W2730231097 hasConcept C2780695682 @default.
- W2730231097 hasConcept C33923547 @default.
- W2730231097 hasConcept C41008148 @default.
- W2730231097 hasConcept C62520636 @default.
- W2730231097 hasConcept C72169020 @default.
- W2730231097 hasConcept C78458016 @default.
- W2730231097 hasConcept C81917197 @default.
- W2730231097 hasConcept C86803240 @default.
- W2730231097 hasConcept C97541855 @default.
- W2730231097 hasConceptScore W2730231097C111472728 @default.
- W2730231097 hasConceptScore W2730231097C11413529 @default.
- W2730231097 hasConceptScore W2730231097C121332964 @default.
- W2730231097 hasConceptScore W2730231097C126255220 @default.
- W2730231097 hasConceptScore W2730231097C126661757 @default.
- W2730231097 hasConceptScore W2730231097C134306372 @default.
- W2730231097 hasConceptScore W2730231097C135320971 @default.
- W2730231097 hasConceptScore W2730231097C138885662 @default.
- W2730231097 hasConceptScore W2730231097C14036430 @default.
- W2730231097 hasConceptScore W2730231097C154945302 @default.
- W2730231097 hasConceptScore W2730231097C2780586882 @default.
- W2730231097 hasConceptScore W2730231097C2780695682 @default.
- W2730231097 hasConceptScore W2730231097C33923547 @default.
- W2730231097 hasConceptScore W2730231097C41008148 @default.
- W2730231097 hasConceptScore W2730231097C62520636 @default.
- W2730231097 hasConceptScore W2730231097C72169020 @default.
- W2730231097 hasConceptScore W2730231097C78458016 @default.
- W2730231097 hasConceptScore W2730231097C81917197 @default.
- W2730231097 hasConceptScore W2730231097C86803240 @default.
- W2730231097 hasConceptScore W2730231097C97541855 @default.
- W2730231097 hasLocation W27302310971 @default.
- W2730231097 hasOpenAccess W2730231097 @default.
- W2730231097 hasPrimaryLocation W27302310971 @default.
- W2730231097 hasRelatedWork W1776957799 @default.
- W2730231097 hasRelatedWork W1901576403 @default.
- W2730231097 hasRelatedWork W2045212467 @default.
- W2730231097 hasRelatedWork W2061586266 @default.
- W2730231097 hasRelatedWork W227666212 @default.
- W2730231097 hasRelatedWork W2292662269 @default.
- W2730231097 hasRelatedWork W2555057479 @default.
- W2730231097 hasRelatedWork W2781869896 @default.
- W2730231097 hasRelatedWork W2807370627 @default.
- W2730231097 hasRelatedWork W2964283858 @default.
- W2730231097 hasRelatedWork W2972788486 @default.
- W2730231097 hasRelatedWork W2991311469 @default.
- W2730231097 hasRelatedWork W3011689844 @default.
- W2730231097 hasRelatedWork W3013116235 @default.
- W2730231097 hasRelatedWork W3014444620 @default.
- W2730231097 hasRelatedWork W3019168126 @default.
- W2730231097 hasRelatedWork W3047043442 @default.
- W2730231097 hasRelatedWork W3107194773 @default.
- W2730231097 hasRelatedWork W3209103956 @default.
- W2730231097 hasRelatedWork W32751321 @default.