Matches in SemOpenAlex for { <https://semopenalex.org/work/W2968800863> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2968800863 abstract "Neuroevolution (i.e., training neural network with Evolution Computation) has successfully unfolded a range of challenging reinforcement learning (RL) tasks. However, existing neuroevolution methods suffer from high sample complexity, as the black-box evaluations (i.e., accumulated rewards of complete Markov Decision Processes (MDPs)) discard bunches of temporal frames (i.e., time-step data instances in MDP). Actually, these temporal frames hold the Markov property of the problem, that benefits the training of neural network as well by temporal difference (TD) learning. In this paper, we propose a memetic reinforcement learning (MRL) framework that optimizes the RL agent by leveraging both black-box evaluations and temporal frames. To this end, an evolution strategy (ES) is associated with Q learning, where ES provides diversified frames to globally train the agent, and Q learning locally exploits the Markov property within frames to refresh the agent. Therefore, MRL conveys a novel memetic framework that allows evaluation free local search by Q learning. Experiments on classical control problem verify the efficiency of the proposed MRL, that achieves significantly faster convergence than canonical ES." @default.
- W2968800863 created "2019-08-22" @default.
- W2968800863 creator A5044443092 @default.
- W2968800863 creator A5048340011 @default.
- W2968800863 creator A5061132796 @default.
- W2968800863 creator A5068243197 @default.
- W2968800863 date "2019-06-01" @default.
- W2968800863 modified "2023-09-27" @default.
- W2968800863 title "Memetic Evolution Strategy for Reinforcement Learning" @default.
- W2968800863 cites W1547737196 @default.
- W2968800863 cites W1559585589 @default.
- W2968800863 cites W1590589195 @default.
- W2968800863 cites W1674110665 @default.
- W2968800863 cites W1949804828 @default.
- W2968800863 cites W2012771980 @default.
- W2968800863 cites W2097437812 @default.
- W2968800863 cites W2101097701 @default.
- W2968800863 cites W2111811973 @default.
- W2968800863 cites W2123859855 @default.
- W2968800863 cites W2137545253 @default.
- W2968800863 cites W2145339207 @default.
- W2968800863 cites W2154047522 @default.
- W2968800863 cites W2257979135 @default.
- W2968800863 cites W2489370762 @default.
- W2968800863 cites W2538642367 @default.
- W2968800863 cites W2557280870 @default.
- W2968800863 cites W2766447205 @default.
- W2968800863 cites W2964025389 @default.
- W2968800863 cites W32403112 @default.
- W2968800863 cites W2131600418 @default.
- W2968800863 doi "https://doi.org/10.1109/cec.2019.8789935" @default.
- W2968800863 hasPublicationYear "2019" @default.
- W2968800863 type Work @default.
- W2968800863 sameAs 2968800863 @default.
- W2968800863 citedByCount "4" @default.
- W2968800863 countsByYear W29688008632019 @default.
- W2968800863 countsByYear W29688008632021 @default.
- W2968800863 countsByYear W29688008632022 @default.
- W2968800863 crossrefType "proceedings-article" @default.
- W2968800863 hasAuthorship W2968800863A5044443092 @default.
- W2968800863 hasAuthorship W2968800863A5048340011 @default.
- W2968800863 hasAuthorship W2968800863A5061132796 @default.
- W2968800863 hasAuthorship W2968800863A5068243197 @default.
- W2968800863 hasConcept C105795698 @default.
- W2968800863 hasConcept C106189395 @default.
- W2968800863 hasConcept C118070581 @default.
- W2968800863 hasConcept C119857082 @default.
- W2968800863 hasConcept C126255220 @default.
- W2968800863 hasConcept C135320971 @default.
- W2968800863 hasConcept C154945302 @default.
- W2968800863 hasConcept C159886148 @default.
- W2968800863 hasConcept C162324750 @default.
- W2968800863 hasConcept C188116033 @default.
- W2968800863 hasConcept C2777303404 @default.
- W2968800863 hasConcept C33923547 @default.
- W2968800863 hasConcept C35129592 @default.
- W2968800863 hasConcept C41008148 @default.
- W2968800863 hasConcept C50522688 @default.
- W2968800863 hasConcept C50644808 @default.
- W2968800863 hasConcept C97541855 @default.
- W2968800863 hasConcept C98763669 @default.
- W2968800863 hasConceptScore W2968800863C105795698 @default.
- W2968800863 hasConceptScore W2968800863C106189395 @default.
- W2968800863 hasConceptScore W2968800863C118070581 @default.
- W2968800863 hasConceptScore W2968800863C119857082 @default.
- W2968800863 hasConceptScore W2968800863C126255220 @default.
- W2968800863 hasConceptScore W2968800863C135320971 @default.
- W2968800863 hasConceptScore W2968800863C154945302 @default.
- W2968800863 hasConceptScore W2968800863C159886148 @default.
- W2968800863 hasConceptScore W2968800863C162324750 @default.
- W2968800863 hasConceptScore W2968800863C188116033 @default.
- W2968800863 hasConceptScore W2968800863C2777303404 @default.
- W2968800863 hasConceptScore W2968800863C33923547 @default.
- W2968800863 hasConceptScore W2968800863C35129592 @default.
- W2968800863 hasConceptScore W2968800863C41008148 @default.
- W2968800863 hasConceptScore W2968800863C50522688 @default.
- W2968800863 hasConceptScore W2968800863C50644808 @default.
- W2968800863 hasConceptScore W2968800863C97541855 @default.
- W2968800863 hasConceptScore W2968800863C98763669 @default.
- W2968800863 hasLocation W29688008631 @default.
- W2968800863 hasOpenAccess W2968800863 @default.
- W2968800863 hasPrimaryLocation W29688008631 @default.
- W2968800863 hasRelatedWork W1973039793 @default.
- W2968800863 hasRelatedWork W2101748387 @default.
- W2968800863 hasRelatedWork W2133178615 @default.
- W2968800863 hasRelatedWork W2145363145 @default.
- W2968800863 hasRelatedWork W2357975469 @default.
- W2968800863 hasRelatedWork W2968800863 @default.
- W2968800863 hasRelatedWork W3089496523 @default.
- W2968800863 hasRelatedWork W3167472281 @default.
- W2968800863 hasRelatedWork W3210863439 @default.
- W2968800863 hasRelatedWork W4286892941 @default.
- W2968800863 isParatext "false" @default.
- W2968800863 isRetracted "false" @default.
- W2968800863 magId "2968800863" @default.
- W2968800863 workType "article" @default.