Matches in SemOpenAlex for { <https://semopenalex.org/work/W2900582619> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W2900582619 endingPage "83" @default.
- W2900582619 startingPage "72" @default.
- W2900582619 abstract "Deep Reinforcement Learning (DRL), which can learn complex policies with high-dimensional observations as inputs, e.g., images, has been successfully applied to various tasks. Therefore, it may be suitable to apply them for robots to learn and perform daily activities like washing and folding clothes, cooking, and cleaning since such tasks are difficult for non-DRL methods that often require either (1) direct access to state variables or (2) well-designed hand-engineered features extracted from sensory inputs. However, applying DRL to real robots remains very challenging because conventional DRL algorithms require a huge number of training samples for learning, which is arduous in real robots. To alleviate this dilemma, in this paper, we propose two sample efficient DRL algorithms: Deep P-Network (DPN) and Dueling Deep P-Network (DDPN). The core idea is to combine the nature of smooth policy update with the capability of automatic feature extraction in deep neural networks to enhance the sample efficiency and learning stability with fewer samples. The proposed methods were first investigated by a robot-arm reaching task in the simulation that compared previous DRL methods and applied to two real robotic cloth manipulation tasks: (1) flipping a handkerchief and (2) folding a t-shirt with a limited number of samples. All the results suggest that our method outperformed the previous DRL methods." @default.
- W2900582619 created "2018-11-29" @default.
- W2900582619 creator A5011048472 @default.
- W2900582619 creator A5031054137 @default.
- W2900582619 creator A5042074952 @default.
- W2900582619 creator A5056162412 @default.
- W2900582619 date "2019-02-01" @default.
- W2900582619 modified "2023-10-04" @default.
- W2900582619 title "Deep reinforcement learning with smooth policy update: Application to robotic cloth manipulation" @default.
- W2900582619 cites W1977655452 @default.
- W2900582619 cites W1982920857 @default.
- W2900582619 cites W2001328977 @default.
- W2900582619 cites W2019267533 @default.
- W2900582619 cites W2033557597 @default.
- W2900582619 cites W2051620263 @default.
- W2900582619 cites W2145339207 @default.
- W2900582619 cites W2147768505 @default.
- W2900582619 cites W2530616813 @default.
- W2900582619 cites W2558355904 @default.
- W2900582619 cites W2587765586 @default.
- W2900582619 cites W2615384492 @default.
- W2900582619 cites W2730929966 @default.
- W2900582619 cites W2760798442 @default.
- W2900582619 cites W2789645218 @default.
- W2900582619 cites W3100789280 @default.
- W2900582619 cites W32403112 @default.
- W2900582619 doi "https://doi.org/10.1016/j.robot.2018.11.004" @default.
- W2900582619 hasPublicationYear "2019" @default.
- W2900582619 type Work @default.
- W2900582619 sameAs 2900582619 @default.
- W2900582619 citedByCount "113" @default.
- W2900582619 countsByYear W29005826192019 @default.
- W2900582619 countsByYear W29005826192020 @default.
- W2900582619 countsByYear W29005826192021 @default.
- W2900582619 countsByYear W29005826192022 @default.
- W2900582619 countsByYear W29005826192023 @default.
- W2900582619 crossrefType "journal-article" @default.
- W2900582619 hasAuthorship W2900582619A5011048472 @default.
- W2900582619 hasAuthorship W2900582619A5031054137 @default.
- W2900582619 hasAuthorship W2900582619A5042074952 @default.
- W2900582619 hasAuthorship W2900582619A5056162412 @default.
- W2900582619 hasBestOaLocation W29005826191 @default.
- W2900582619 hasConcept C154945302 @default.
- W2900582619 hasConcept C41008148 @default.
- W2900582619 hasConcept C97541855 @default.
- W2900582619 hasConceptScore W2900582619C154945302 @default.
- W2900582619 hasConceptScore W2900582619C41008148 @default.
- W2900582619 hasConceptScore W2900582619C97541855 @default.
- W2900582619 hasLocation W29005826191 @default.
- W2900582619 hasOpenAccess W2900582619 @default.
- W2900582619 hasPrimaryLocation W29005826191 @default.
- W2900582619 hasRelatedWork W2923653485 @default.
- W2900582619 hasRelatedWork W2952472710 @default.
- W2900582619 hasRelatedWork W2957776456 @default.
- W2900582619 hasRelatedWork W2959276766 @default.
- W2900582619 hasRelatedWork W3005560120 @default.
- W2900582619 hasRelatedWork W3037422413 @default.
- W2900582619 hasRelatedWork W4206669594 @default.
- W2900582619 hasRelatedWork W4224287422 @default.
- W2900582619 hasRelatedWork W4255994452 @default.
- W2900582619 hasRelatedWork W4319773215 @default.
- W2900582619 hasVolume "112" @default.
- W2900582619 isParatext "false" @default.
- W2900582619 isRetracted "false" @default.
- W2900582619 magId "2900582619" @default.
- W2900582619 workType "article" @default.