Matches in SemOpenAlex for { <https://semopenalex.org/work/W2914987759> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2914987759 abstract "Deep learning has achieved a great success in both visual and acoustic recognition and classification tasks. The accuracy of many state-of-the-art methods have surpassed that of human beings. However, in the field of robotics, it remains to be a big challenge for a real robot to master a high-level skill using deep learning methods, even though human can easily learn the task from demonstration, imitation and practice. Compared to Go and Atari games, this kind of tasks is usually continuous in both state space and action space, which makes value based reinforcement learning methods unavailable. Making a robot learn to return a ball to a desired point in table tennis is such a typical task. It would be a promising step if a robot can learn to play table tennis without the exact knowledge of the models in this sport just as human players do. In this paper, we consider such a kind of motion decision skill learning, a one-step decision making process, and give a Monte-Carlo based reinforcement learning method in the framework of Deep Deterministic Policy Gradient. Then we apply this method in robotic table tennis and test it on two tasks. The first one is to return balls to a desired point first, and the second one is to return balls to randomly selected landing points. The experimental results demonstrate that the trained policy can successfully return balls of random motion state to both a designated point and randomly selected landing points with high accuracy." @default.
- W2914987759 created "2019-02-21" @default.
- W2914987759 creator A5012472163 @default.
- W2914987759 creator A5019081110 @default.
- W2914987759 creator A5024847384 @default.
- W2914987759 creator A5035249197 @default.
- W2914987759 creator A5061317219 @default.
- W2914987759 date "2018-08-01" @default.
- W2914987759 modified "2023-09-25" @default.
- W2914987759 title "Towards High Level Skill Learning: Learn to Return Table Tennis Ball Using Monte-Carlo Based Policy Gradient Method" @default.
- W2914987759 cites W2012204020 @default.
- W2914987759 cites W204153720 @default.
- W2914987759 cites W2059698169 @default.
- W2914987759 cites W2111978237 @default.
- W2914987759 cites W2113501460 @default.
- W2914987759 cites W2142300342 @default.
- W2914987759 cites W2144576818 @default.
- W2914987759 cites W2145339207 @default.
- W2914987759 cites W2172968643 @default.
- W2914987759 cites W2257979135 @default.
- W2914987759 cites W2385601253 @default.
- W2914987759 cites W2443711627 @default.
- W2914987759 doi "https://doi.org/10.1109/rcar.2018.8621776" @default.
- W2914987759 hasPublicationYear "2018" @default.
- W2914987759 type Work @default.
- W2914987759 sameAs 2914987759 @default.
- W2914987759 citedByCount "11" @default.
- W2914987759 countsByYear W29149877592020 @default.
- W2914987759 countsByYear W29149877592021 @default.
- W2914987759 countsByYear W29149877592022 @default.
- W2914987759 countsByYear W29149877592023 @default.
- W2914987759 crossrefType "proceedings-article" @default.
- W2914987759 hasAuthorship W2914987759A5012472163 @default.
- W2914987759 hasAuthorship W2914987759A5019081110 @default.
- W2914987759 hasAuthorship W2914987759A5024847384 @default.
- W2914987759 hasAuthorship W2914987759A5035249197 @default.
- W2914987759 hasAuthorship W2914987759A5061317219 @default.
- W2914987759 hasConcept C105795698 @default.
- W2914987759 hasConcept C119857082 @default.
- W2914987759 hasConcept C122041747 @default.
- W2914987759 hasConcept C127413603 @default.
- W2914987759 hasConcept C134306372 @default.
- W2914987759 hasConcept C154945302 @default.
- W2914987759 hasConcept C19499675 @default.
- W2914987759 hasConcept C201995342 @default.
- W2914987759 hasConcept C2780101202 @default.
- W2914987759 hasConcept C2780451532 @default.
- W2914987759 hasConcept C2992174615 @default.
- W2914987759 hasConcept C31972630 @default.
- W2914987759 hasConcept C33923547 @default.
- W2914987759 hasConcept C41008148 @default.
- W2914987759 hasConcept C78519656 @default.
- W2914987759 hasConcept C90509273 @default.
- W2914987759 hasConcept C97541855 @default.
- W2914987759 hasConceptScore W2914987759C105795698 @default.
- W2914987759 hasConceptScore W2914987759C119857082 @default.
- W2914987759 hasConceptScore W2914987759C122041747 @default.
- W2914987759 hasConceptScore W2914987759C127413603 @default.
- W2914987759 hasConceptScore W2914987759C134306372 @default.
- W2914987759 hasConceptScore W2914987759C154945302 @default.
- W2914987759 hasConceptScore W2914987759C19499675 @default.
- W2914987759 hasConceptScore W2914987759C201995342 @default.
- W2914987759 hasConceptScore W2914987759C2780101202 @default.
- W2914987759 hasConceptScore W2914987759C2780451532 @default.
- W2914987759 hasConceptScore W2914987759C2992174615 @default.
- W2914987759 hasConceptScore W2914987759C31972630 @default.
- W2914987759 hasConceptScore W2914987759C33923547 @default.
- W2914987759 hasConceptScore W2914987759C41008148 @default.
- W2914987759 hasConceptScore W2914987759C78519656 @default.
- W2914987759 hasConceptScore W2914987759C90509273 @default.
- W2914987759 hasConceptScore W2914987759C97541855 @default.
- W2914987759 hasLocation W29149877591 @default.
- W2914987759 hasOpenAccess W2914987759 @default.
- W2914987759 hasPrimaryLocation W29149877591 @default.
- W2914987759 hasRelatedWork W1891287906 @default.
- W2914987759 hasRelatedWork W2577012160 @default.
- W2914987759 hasRelatedWork W2592061664 @default.
- W2914987759 hasRelatedWork W2959276766 @default.
- W2914987759 hasRelatedWork W2961085424 @default.
- W2914987759 hasRelatedWork W3074294383 @default.
- W2914987759 hasRelatedWork W3127601461 @default.
- W2914987759 hasRelatedWork W4206669594 @default.
- W2914987759 hasRelatedWork W4295941380 @default.
- W2914987759 hasRelatedWork W4319083788 @default.
- W2914987759 isParatext "false" @default.
- W2914987759 isRetracted "false" @default.
- W2914987759 magId "2914987759" @default.
- W2914987759 workType "article" @default.