Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206461631> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4206461631 abstract "Reinforcement learning (RL) has been extensively studied for robotic skill acquisition. Nevertheless, existing methods require extensive environmental interactions or high-quality demonstrations, which limits their application in practice. To alleviate this problem, a practical algorithm, named self-imitation learning with guide reward (SILGR), is proposed. The algorithm selects relatively good trajectories as expert data instead of external demonstrations and then assigns a guide reward to each transition. The criterion of the guide reward generator improves consistently with the evolution of the agent. In this way, the agent explores the environment in a task-relevant direction and exploits the experience more effectively, improving sample efficiency and performance. The results on four continuous locomotion tasks indicate that the proposed scheme achieves better performance than other state-of-the-art deep RL methods." @default.
- W4206461631 created "2022-01-25" @default.
- W4206461631 creator A5058806378 @default.
- W4206461631 creator A5084573070 @default.
- W4206461631 date "2021-10-17" @default.
- W4206461631 modified "2023-09-29" @default.
- W4206461631 title "Learning Robotic Skills via Self-Imitation and Guide Reward" @default.
- W4206461631 cites W2145339207 @default.
- W4206461631 cites W2257979135 @default.
- W4206461631 cites W2766447205 @default.
- W4206461631 cites W2910054127 @default.
- W4206461631 cites W2956001080 @default.
- W4206461631 cites W2963669336 @default.
- W4206461631 cites W2963761387 @default.
- W4206461631 cites W2986925736 @default.
- W4206461631 cites W3000280594 @default.
- W4206461631 cites W3034269714 @default.
- W4206461631 cites W3188004887 @default.
- W4206461631 doi "https://doi.org/10.1109/smc52423.2021.9658945" @default.
- W4206461631 hasPublicationYear "2021" @default.
- W4206461631 type Work @default.
- W4206461631 citedByCount "1" @default.
- W4206461631 countsByYear W42064616312023 @default.
- W4206461631 crossrefType "proceedings-article" @default.
- W4206461631 hasAuthorship W4206461631A5058806378 @default.
- W4206461631 hasAuthorship W4206461631A5084573070 @default.
- W4206461631 hasConcept C111472728 @default.
- W4206461631 hasConcept C119857082 @default.
- W4206461631 hasConcept C121332964 @default.
- W4206461631 hasConcept C126388530 @default.
- W4206461631 hasConcept C127413603 @default.
- W4206461631 hasConcept C134306372 @default.
- W4206461631 hasConcept C138885662 @default.
- W4206461631 hasConcept C154945302 @default.
- W4206461631 hasConcept C15744967 @default.
- W4206461631 hasConcept C163258240 @default.
- W4206461631 hasConcept C165696696 @default.
- W4206461631 hasConcept C201995342 @default.
- W4206461631 hasConcept C2779530757 @default.
- W4206461631 hasConcept C2780451532 @default.
- W4206461631 hasConcept C2780992000 @default.
- W4206461631 hasConcept C33923547 @default.
- W4206461631 hasConcept C38652104 @default.
- W4206461631 hasConcept C41008148 @default.
- W4206461631 hasConcept C62520636 @default.
- W4206461631 hasConcept C77618280 @default.
- W4206461631 hasConcept C77805123 @default.
- W4206461631 hasConcept C90509273 @default.
- W4206461631 hasConcept C97541855 @default.
- W4206461631 hasConceptScore W4206461631C111472728 @default.
- W4206461631 hasConceptScore W4206461631C119857082 @default.
- W4206461631 hasConceptScore W4206461631C121332964 @default.
- W4206461631 hasConceptScore W4206461631C126388530 @default.
- W4206461631 hasConceptScore W4206461631C127413603 @default.
- W4206461631 hasConceptScore W4206461631C134306372 @default.
- W4206461631 hasConceptScore W4206461631C138885662 @default.
- W4206461631 hasConceptScore W4206461631C154945302 @default.
- W4206461631 hasConceptScore W4206461631C15744967 @default.
- W4206461631 hasConceptScore W4206461631C163258240 @default.
- W4206461631 hasConceptScore W4206461631C165696696 @default.
- W4206461631 hasConceptScore W4206461631C201995342 @default.
- W4206461631 hasConceptScore W4206461631C2779530757 @default.
- W4206461631 hasConceptScore W4206461631C2780451532 @default.
- W4206461631 hasConceptScore W4206461631C2780992000 @default.
- W4206461631 hasConceptScore W4206461631C33923547 @default.
- W4206461631 hasConceptScore W4206461631C38652104 @default.
- W4206461631 hasConceptScore W4206461631C41008148 @default.
- W4206461631 hasConceptScore W4206461631C62520636 @default.
- W4206461631 hasConceptScore W4206461631C77618280 @default.
- W4206461631 hasConceptScore W4206461631C77805123 @default.
- W4206461631 hasConceptScore W4206461631C90509273 @default.
- W4206461631 hasConceptScore W4206461631C97541855 @default.
- W4206461631 hasFunder F4320321001 @default.
- W4206461631 hasLocation W42064616311 @default.
- W4206461631 hasOpenAccess W4206461631 @default.
- W4206461631 hasPrimaryLocation W42064616311 @default.
- W4206461631 hasRelatedWork W1596397513 @default.
- W4206461631 hasRelatedWork W2097364276 @default.
- W4206461631 hasRelatedWork W2616430965 @default.
- W4206461631 hasRelatedWork W2795910581 @default.
- W4206461631 hasRelatedWork W3022038857 @default.
- W4206461631 hasRelatedWork W4206461631 @default.
- W4206461631 hasRelatedWork W4210901955 @default.
- W4206461631 hasRelatedWork W4225854080 @default.
- W4206461631 hasRelatedWork W4309675293 @default.
- W4206461631 hasRelatedWork W4319083788 @default.
- W4206461631 isParatext "false" @default.
- W4206461631 isRetracted "false" @default.
- W4206461631 workType "article" @default.