FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206200647> ?p ?o ?g. }

• W3206200647 abstract "Reinforcement Learning (RL) algorithms can in principle acquire complex robotic skills by learning from large amounts of data in the real world, collected via trial and error. However, most RL algorithms use a carefully engineered setup in order to collect data, requiring human supervision and intervention to provide episodic resets. This is particularly evident in challenging robotics problems, such as dexterous manipulation. To make data collection scalable, such applications require reset-free algorithms that are able to learn autonomously, without explicit instrumentation or human intervention. Most prior work in this area handles single-task learning. However, we might also want robots that can perform large repertoires of skills. At first, this would appear to only make the problem harder. However, the key observation we make in this work is that an appropriately chosen multi-task RL setting actually alleviates the reset-free learning challenge, with minimal additional machinery required. In effect, solving a multi-task problem can directly solve the reset-free problem since different combinations of tasks can serve to perform resets for other tasks. By learning multiple tasks together and appropriately sequencing them, we can effectively learn all of the tasks together reset-free. This type of multi-task learning can effectively scale reset-free learning schemes to much more complex problems, as we demonstrate in our experiments. We propose a simple scheme for multi-task learning that tackles the reset-free learning problem, and show its effectiveness at learning to solve complex dexterous manipulation tasks in both hardware and simulation without any explicit resets. This work shows the ability to learn in-hand manipulation behaviors in the real world with RL without any human intervention." @default.
• W3206200647 created "2021-10-25" @default.
• W3206200647 creator A5003090942 @default.
• W3206200647 creator A5006434815 @default.
• W3206200647 creator A5017906439 @default.
• W3206200647 creator A5026322200 @default.
• W3206200647 creator A5027007388 @default.
• W3206200647 creator A5041306134 @default.
• W3206200647 creator A5045672280 @default.
• W3206200647 creator A5060717631 @default.
• W3206200647 date "2021-05-30" @default.
• W3206200647 modified "2023-10-01" @default.
• W3206200647 title "Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention" @default.
• W3206200647 cites W1969074599 @default.
• W3206200647 cites W2019165997 @default.
• W3206200647 cites W2073408938 @default.
• W3206200647 cites W2112036576 @default.
• W3206200647 cites W2126909264 @default.
• W3206200647 cites W2129629060 @default.
• W3206200647 cites W2161273941 @default.
• W3206200647 cites W2201912979 @default.
• W3206200647 cites W2210408922 @default.
• W3206200647 cites W2221677593 @default.
• W3206200647 cites W2416041116 @default.
• W3206200647 cites W2592538810 @default.
• W3206200647 cites W2734960757 @default.
• W3206200647 cites W2753818635 @default.
• W3206200647 cites W2789805345 @default.
• W3206200647 cites W2796290181 @default.
• W3206200647 cites W2963170432 @default.
• W3206200647 cites W2968340082 @default.
• W3206200647 cites W2990747716 @default.
• W3206200647 cites W4244930641 @default.
• W3206200647 cites W770013183 @default.
• W3206200647 doi "https://doi.org/10.1109/icra48506.2021.9561384" @default.
• W3206200647 hasPublicationYear "2021" @default.
• W3206200647 type Work @default.
• W3206200647 sameAs 3206200647 @default.
• W3206200647 citedByCount "12" @default.
• W3206200647 countsByYear W32062006472021 @default.
• W3206200647 countsByYear W32062006472022 @default.
• W3206200647 countsByYear W32062006472023 @default.
• W3206200647 crossrefType "proceedings-article" @default.
• W3206200647 hasAuthorship W3206200647A5003090942 @default.
• W3206200647 hasAuthorship W3206200647A5006434815 @default.
• W3206200647 hasAuthorship W3206200647A5017906439 @default.
• W3206200647 hasAuthorship W3206200647A5026322200 @default.
• W3206200647 hasAuthorship W3206200647A5027007388 @default.
• W3206200647 hasAuthorship W3206200647A5041306134 @default.
• W3206200647 hasAuthorship W3206200647A5045672280 @default.
• W3206200647 hasAuthorship W3206200647A5060717631 @default.
• W3206200647 hasBestOaLocation W32062006472 @default.
• W3206200647 hasConcept C106159729 @default.
• W3206200647 hasConcept C107457646 @default.
• W3206200647 hasConcept C119857082 @default.
• W3206200647 hasConcept C127413603 @default.
• W3206200647 hasConcept C154945302 @default.
• W3206200647 hasConcept C162324750 @default.
• W3206200647 hasConcept C188888258 @default.
• W3206200647 hasConcept C19966478 @default.
• W3206200647 hasConcept C201995342 @default.
• W3206200647 hasConcept C2779795794 @default.
• W3206200647 hasConcept C2780451532 @default.
• W3206200647 hasConcept C28006648 @default.
• W3206200647 hasConcept C34413123 @default.
• W3206200647 hasConcept C41008148 @default.
• W3206200647 hasConcept C48044578 @default.
• W3206200647 hasConcept C77088390 @default.
• W3206200647 hasConcept C90509273 @default.
• W3206200647 hasConcept C97541855 @default.
• W3206200647 hasConceptScore W3206200647C106159729 @default.
• W3206200647 hasConceptScore W3206200647C107457646 @default.
• W3206200647 hasConceptScore W3206200647C119857082 @default.
• W3206200647 hasConceptScore W3206200647C127413603 @default.
• W3206200647 hasConceptScore W3206200647C154945302 @default.
• W3206200647 hasConceptScore W3206200647C162324750 @default.
• W3206200647 hasConceptScore W3206200647C188888258 @default.
• W3206200647 hasConceptScore W3206200647C19966478 @default.
• W3206200647 hasConceptScore W3206200647C201995342 @default.
• W3206200647 hasConceptScore W3206200647C2779795794 @default.
• W3206200647 hasConceptScore W3206200647C2780451532 @default.
• W3206200647 hasConceptScore W3206200647C28006648 @default.
• W3206200647 hasConceptScore W3206200647C34413123 @default.
• W3206200647 hasConceptScore W3206200647C41008148 @default.
• W3206200647 hasConceptScore W3206200647C48044578 @default.
• W3206200647 hasConceptScore W3206200647C77088390 @default.
• W3206200647 hasConceptScore W3206200647C90509273 @default.
• W3206200647 hasConceptScore W3206200647C97541855 @default.
• W3206200647 hasFunder F4320306076 @default.
• W3206200647 hasFunder F4320337345 @default.
• W3206200647 hasLocation W32062006471 @default.
• W3206200647 hasLocation W32062006472 @default.
• W3206200647 hasOpenAccess W3206200647 @default.
• W3206200647 hasPrimaryLocation W32062006471 @default.
• W3206200647 hasRelatedWork W1582995160 @default.
• W3206200647 hasRelatedWork W1763389228 @default.
• W3206200647 hasRelatedWork W2065963568 @default.
• W3206200647 hasRelatedWork W2325123304 @default.
• W3206200647 hasRelatedWork W2343019076 @default.
• W3206200647 hasRelatedWork W2787824708 @default.

• next