Matches in SemOpenAlex for { <https://semopenalex.org/work/W2906917062> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2906917062 abstract "In this paper, we propose a novel meta-learning method in a reinforcement learning setting, based on evolution strategies (ES), exploration in parameter space and deterministic policy gradients. ES methods are easy to parallelize, which is desirable for modern training architectures; however, such methods typically require a huge number of samples for effective training. We use deterministic policy gradients during adaptation and other techniques to compensate for the sample-efficiency problem while maintaining the inherent scalability of ES methods. We demonstrate that our method achieves good results compared to gradient-based meta-learning in high-dimensional control tasks in the MuJoCo simulator. In addition, because of gradient-free methods in the meta-training phase, which do not need information about gradients and policies in adaptation training, we predict and confirm our algorithm performs better in tasks that need multi-step adaptation." @default.
- W2906917062 created "2019-01-11" @default.
- W2906917062 creator A5015257582 @default.
- W2906917062 creator A5042954876 @default.
- W2906917062 creator A5052859737 @default.
- W2906917062 creator A5088680274 @default.
- W2906917062 date "2018-12-29" @default.
- W2906917062 modified "2023-09-27" @default.
- W2906917062 title "Meta Reinforcement Learning with Distribution of Exploration Parameters Learned by Evolution Strategies" @default.
- W2906917062 cites W123765585 @default.
- W2906917062 cites W1522301498 @default.
- W2906917062 cites W1757796397 @default.
- W2906917062 cites W2145339207 @default.
- W2906917062 cites W2151965738 @default.
- W2906917062 cites W2155027007 @default.
- W2906917062 cites W2158782408 @default.
- W2906917062 cites W2173248099 @default.
- W2906917062 cites W2257979135 @default.
- W2906917062 cites W2288565641 @default.
- W2906917062 cites W2596367596 @default.
- W2906917062 cites W2604763608 @default.
- W2906917062 cites W2766447205 @default.
- W2906917062 cites W2808809512 @default.
- W2906917062 cites W2963024489 @default.
- W2906917062 cites W2963641140 @default.
- W2906917062 cites W2770298516 @default.
- W2906917062 hasPublicationYear "2018" @default.
- W2906917062 type Work @default.
- W2906917062 sameAs 2906917062 @default.
- W2906917062 citedByCount "0" @default.
- W2906917062 crossrefType "posted-content" @default.
- W2906917062 hasAuthorship W2906917062A5015257582 @default.
- W2906917062 hasAuthorship W2906917062A5042954876 @default.
- W2906917062 hasAuthorship W2906917062A5052859737 @default.
- W2906917062 hasAuthorship W2906917062A5088680274 @default.
- W2906917062 hasConcept C119857082 @default.
- W2906917062 hasConcept C120665830 @default.
- W2906917062 hasConcept C121332964 @default.
- W2906917062 hasConcept C127413603 @default.
- W2906917062 hasConcept C139807058 @default.
- W2906917062 hasConcept C154945302 @default.
- W2906917062 hasConcept C185592680 @default.
- W2906917062 hasConcept C198531522 @default.
- W2906917062 hasConcept C201995342 @default.
- W2906917062 hasConcept C2775924081 @default.
- W2906917062 hasConcept C2780451532 @default.
- W2906917062 hasConcept C2781002164 @default.
- W2906917062 hasConcept C41008148 @default.
- W2906917062 hasConcept C43617362 @default.
- W2906917062 hasConcept C48044578 @default.
- W2906917062 hasConcept C77088390 @default.
- W2906917062 hasConcept C97541855 @default.
- W2906917062 hasConceptScore W2906917062C119857082 @default.
- W2906917062 hasConceptScore W2906917062C120665830 @default.
- W2906917062 hasConceptScore W2906917062C121332964 @default.
- W2906917062 hasConceptScore W2906917062C127413603 @default.
- W2906917062 hasConceptScore W2906917062C139807058 @default.
- W2906917062 hasConceptScore W2906917062C154945302 @default.
- W2906917062 hasConceptScore W2906917062C185592680 @default.
- W2906917062 hasConceptScore W2906917062C198531522 @default.
- W2906917062 hasConceptScore W2906917062C201995342 @default.
- W2906917062 hasConceptScore W2906917062C2775924081 @default.
- W2906917062 hasConceptScore W2906917062C2780451532 @default.
- W2906917062 hasConceptScore W2906917062C2781002164 @default.
- W2906917062 hasConceptScore W2906917062C41008148 @default.
- W2906917062 hasConceptScore W2906917062C43617362 @default.
- W2906917062 hasConceptScore W2906917062C48044578 @default.
- W2906917062 hasConceptScore W2906917062C77088390 @default.
- W2906917062 hasConceptScore W2906917062C97541855 @default.
- W2906917062 hasLocation W29069170621 @default.
- W2906917062 hasOpenAccess W2906917062 @default.
- W2906917062 hasPrimaryLocation W29069170621 @default.
- W2906917062 hasRelatedWork W2626860042 @default.
- W2906917062 hasRelatedWork W2946299167 @default.
- W2906917062 hasRelatedWork W2952193948 @default.
- W2906917062 hasRelatedWork W2952526277 @default.
- W2906917062 hasRelatedWork W2959218200 @default.
- W2906917062 hasRelatedWork W2962872206 @default.
- W2906917062 hasRelatedWork W2978438412 @default.
- W2906917062 hasRelatedWork W2982795998 @default.
- W2906917062 hasRelatedWork W2992534497 @default.
- W2906917062 hasRelatedWork W2995892679 @default.
- W2906917062 hasRelatedWork W3010862467 @default.
- W2906917062 hasRelatedWork W3011311310 @default.
- W2906917062 hasRelatedWork W3035216917 @default.
- W2906917062 hasRelatedWork W3035689006 @default.
- W2906917062 hasRelatedWork W3091795298 @default.
- W2906917062 hasRelatedWork W3093147807 @default.
- W2906917062 hasRelatedWork W3093382707 @default.
- W2906917062 hasRelatedWork W3160665951 @default.
- W2906917062 hasRelatedWork W3166476084 @default.
- W2906917062 hasRelatedWork W3175558129 @default.
- W2906917062 isParatext "false" @default.
- W2906917062 isRetracted "false" @default.
- W2906917062 magId "2906917062" @default.
- W2906917062 workType "article" @default.