Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100908797> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3100908797 endingPage "17465" @default.
- W3100908797 startingPage "17455" @default.
- W3100908797 abstract "Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep Reinforcement Learning (CHDRL) framework that can learn a policy by integrating the advantages of heterogeneous agents. Specifically, we propose a cooperative learning framework that classifies heterogeneous agents into two classes: global agents and local agents. Global agents are off-policy agents that can utilize experiences from the other agents. Local agents are either on-policy agents or population-based evolutionary algorithms (EAs) agents that can explore the local area effectively. We employ global agents, which are sample-efficient, to guide the learning of local agents so that local agents can benefit from sample-efficient agents and simultaneously maintain their advantages, e.g., stability. Global agents also benefit from effective local searches. Experimental studies on a range of continuous control tasks from the Mujoco benchmark show that CHDRL achieves better performance compared with state-of-the-art baselines." @default.
- W3100908797 created "2020-11-23" @default.
- W3100908797 creator A5015951797 @default.
- W3100908797 creator A5045781240 @default.
- W3100908797 creator A5057139422 @default.
- W3100908797 creator A5059227406 @default.
- W3100908797 creator A5074852078 @default.
- W3100908797 creator A5084232243 @default.
- W3100908797 date "2020-01-01" @default.
- W3100908797 modified "2023-10-08" @default.
- W3100908797 title "Cooperative Heterogeneous Deep Reinforcement Learning" @default.
- W3100908797 hasPublicationYear "2020" @default.
- W3100908797 type Work @default.
- W3100908797 sameAs 3100908797 @default.
- W3100908797 citedByCount "0" @default.
- W3100908797 crossrefType "proceedings-article" @default.
- W3100908797 hasAuthorship W3100908797A5015951797 @default.
- W3100908797 hasAuthorship W3100908797A5045781240 @default.
- W3100908797 hasAuthorship W3100908797A5057139422 @default.
- W3100908797 hasAuthorship W3100908797A5059227406 @default.
- W3100908797 hasAuthorship W3100908797A5074852078 @default.
- W3100908797 hasAuthorship W3100908797A5084232243 @default.
- W3100908797 hasConcept C112972136 @default.
- W3100908797 hasConcept C119857082 @default.
- W3100908797 hasConcept C127413603 @default.
- W3100908797 hasConcept C13280743 @default.
- W3100908797 hasConcept C144024400 @default.
- W3100908797 hasConcept C146978453 @default.
- W3100908797 hasConcept C149923435 @default.
- W3100908797 hasConcept C154945302 @default.
- W3100908797 hasConcept C185592680 @default.
- W3100908797 hasConcept C185798385 @default.
- W3100908797 hasConcept C198531522 @default.
- W3100908797 hasConcept C204323151 @default.
- W3100908797 hasConcept C205649164 @default.
- W3100908797 hasConcept C2908647359 @default.
- W3100908797 hasConcept C41008148 @default.
- W3100908797 hasConcept C41550386 @default.
- W3100908797 hasConcept C43617362 @default.
- W3100908797 hasConcept C97541855 @default.
- W3100908797 hasConceptScore W3100908797C112972136 @default.
- W3100908797 hasConceptScore W3100908797C119857082 @default.
- W3100908797 hasConceptScore W3100908797C127413603 @default.
- W3100908797 hasConceptScore W3100908797C13280743 @default.
- W3100908797 hasConceptScore W3100908797C144024400 @default.
- W3100908797 hasConceptScore W3100908797C146978453 @default.
- W3100908797 hasConceptScore W3100908797C149923435 @default.
- W3100908797 hasConceptScore W3100908797C154945302 @default.
- W3100908797 hasConceptScore W3100908797C185592680 @default.
- W3100908797 hasConceptScore W3100908797C185798385 @default.
- W3100908797 hasConceptScore W3100908797C198531522 @default.
- W3100908797 hasConceptScore W3100908797C204323151 @default.
- W3100908797 hasConceptScore W3100908797C205649164 @default.
- W3100908797 hasConceptScore W3100908797C2908647359 @default.
- W3100908797 hasConceptScore W3100908797C41008148 @default.
- W3100908797 hasConceptScore W3100908797C41550386 @default.
- W3100908797 hasConceptScore W3100908797C43617362 @default.
- W3100908797 hasConceptScore W3100908797C97541855 @default.
- W3100908797 hasLocation W31009087971 @default.
- W3100908797 hasOpenAccess W3100908797 @default.
- W3100908797 hasPrimaryLocation W31009087971 @default.
- W3100908797 hasRelatedWork W1504806788 @default.
- W3100908797 hasRelatedWork W2261683202 @default.
- W3100908797 hasRelatedWork W2731184740 @default.
- W3100908797 hasRelatedWork W2757927221 @default.
- W3100908797 hasRelatedWork W2940957092 @default.
- W3100908797 hasRelatedWork W2947287992 @default.
- W3100908797 hasRelatedWork W2980784261 @default.
- W3100908797 hasRelatedWork W3037399051 @default.
- W3100908797 hasRelatedWork W3047315308 @default.
- W3100908797 hasRelatedWork W3112808542 @default.
- W3100908797 hasRelatedWork W3121258823 @default.
- W3100908797 hasRelatedWork W3131922376 @default.
- W3100908797 hasRelatedWork W3161195296 @default.
- W3100908797 hasRelatedWork W3168434473 @default.
- W3100908797 hasRelatedWork W3170473100 @default.
- W3100908797 hasRelatedWork W3185202350 @default.
- W3100908797 hasRelatedWork W3200847968 @default.
- W3100908797 hasRelatedWork W3201019068 @default.
- W3100908797 hasRelatedWork W3207471418 @default.
- W3100908797 hasRelatedWork W75348631 @default.
- W3100908797 hasVolume "33" @default.
- W3100908797 isParatext "false" @default.
- W3100908797 isRetracted "false" @default.
- W3100908797 magId "3100908797" @default.
- W3100908797 workType "article" @default.