Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080433414> ?p ?o ?g. }
- W3080433414 abstract "Modern Reinforcement Learning (RL) algorithms promise to solve difficult motor control problems directly from raw sensory inputs. Their attraction is due in part to the fact that they can represent a general class of methods that allow to learn a solution with a reasonably set reward and minimal prior knowledge, even in situations where it is difficult or expensive for a human expert. For RL to truly make good on this promise, however, we need algorithms and learning setups that can work across a broad range of problems with minimal problem specific adjustments or engineering. In this paper, we study this idea of generality in the locomotion domain. We develop a learning framework that can learn sophisticated locomotion behavior for a wide spectrum of legged robots, such as bipeds, tripeds, quadrupeds and hexapods, including wheeled variants. Our learning framework relies on a data-efficient, off-policy multi-task RL algorithm and a small set of reward functions that are semantically identical across robots. To underline the general applicability of the method, we keep the hyper-parameter settings and reward definitions constant across experiments and rely exclusively on on-board sensing. For nine different types of robots, including a real-world quadruped robot, we demonstrate that the same algorithm can rapidly learn diverse and reusable locomotion skills without any platform specific adjustments or additional instrumentation of the learning setup." @default.
- W3080433414 created "2020-09-01" @default.
- W3080433414 creator A5002747297 @default.
- W3080433414 creator A5004482443 @default.
- W3080433414 creator A5018196238 @default.
- W3080433414 creator A5026388725 @default.
- W3080433414 creator A5041323275 @default.
- W3080433414 creator A5044558749 @default.
- W3080433414 creator A5053312475 @default.
- W3080433414 creator A5062951341 @default.
- W3080433414 creator A5077653936 @default.
- W3080433414 date "2020-08-06" @default.
- W3080433414 modified "2023-09-27" @default.
- W3080433414 title "Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion" @default.
- W3080433414 cites W1822001265 @default.
- W3080433414 cites W1969366849 @default.
- W3080433414 cites W2111904757 @default.
- W3080433414 cites W2144351850 @default.
- W3080433414 cites W2158782408 @default.
- W3080433414 cites W2198582666 @default.
- W3080433414 cites W2534060593 @default.
- W3080433414 cites W2556477470 @default.
- W3080433414 cites W2726187156 @default.
- W3080433414 cites W2755469532 @default.
- W3080433414 cites W2785342287 @default.
- W3080433414 cites W2788030459 @default.
- W3080433414 cites W2900397023 @default.
- W3080433414 cites W2902711054 @default.
- W3080433414 cites W2907537824 @default.
- W3080433414 cites W2909331752 @default.
- W3080433414 cites W2909553221 @default.
- W3080433414 cites W2911087563 @default.
- W3080433414 cites W2911618937 @default.
- W3080433414 cites W2919616510 @default.
- W3080433414 cites W2963438456 @default.
- W3080433414 cites W2963960193 @default.
- W3080433414 cites W2964118020 @default.
- W3080433414 cites W2968800739 @default.
- W3080433414 cites W2970990801 @default.
- W3080433414 cites W2975869184 @default.
- W3080433414 cites W2976999889 @default.
- W3080433414 cites W2991389670 @default.
- W3080433414 cites W2998488389 @default.
- W3080433414 cites W3014488508 @default.
- W3080433414 cites W3024554557 @default.
- W3080433414 cites W3027456239 @default.
- W3080433414 cites W3029641972 @default.
- W3080433414 cites W3101817006 @default.
- W3080433414 cites W3102051120 @default.
- W3080433414 cites W3208422024 @default.
- W3080433414 cites W3020283675 @default.
- W3080433414 hasPublicationYear "2020" @default.
- W3080433414 type Work @default.
- W3080433414 sameAs 3080433414 @default.
- W3080433414 citedByCount "4" @default.
- W3080433414 countsByYear W30804334142021 @default.
- W3080433414 countsByYear W30804334142023 @default.
- W3080433414 crossrefType "posted-content" @default.
- W3080433414 hasAuthorship W3080433414A5002747297 @default.
- W3080433414 hasAuthorship W3080433414A5004482443 @default.
- W3080433414 hasAuthorship W3080433414A5018196238 @default.
- W3080433414 hasAuthorship W3080433414A5026388725 @default.
- W3080433414 hasAuthorship W3080433414A5041323275 @default.
- W3080433414 hasAuthorship W3080433414A5044558749 @default.
- W3080433414 hasAuthorship W3080433414A5053312475 @default.
- W3080433414 hasAuthorship W3080433414A5062951341 @default.
- W3080433414 hasAuthorship W3080433414A5077653936 @default.
- W3080433414 hasConcept C107457646 @default.
- W3080433414 hasConcept C119857082 @default.
- W3080433414 hasConcept C127413603 @default.
- W3080433414 hasConcept C134306372 @default.
- W3080433414 hasConcept C154945302 @default.
- W3080433414 hasConcept C15744967 @default.
- W3080433414 hasConcept C177264268 @default.
- W3080433414 hasConcept C199360897 @default.
- W3080433414 hasConcept C201995342 @default.
- W3080433414 hasConcept C2777212361 @default.
- W3080433414 hasConcept C2780451532 @default.
- W3080433414 hasConcept C2780767217 @default.
- W3080433414 hasConcept C33923547 @default.
- W3080433414 hasConcept C36503486 @default.
- W3080433414 hasConcept C41008148 @default.
- W3080433414 hasConcept C542102704 @default.
- W3080433414 hasConcept C90509273 @default.
- W3080433414 hasConcept C97541855 @default.
- W3080433414 hasConceptScore W3080433414C107457646 @default.
- W3080433414 hasConceptScore W3080433414C119857082 @default.
- W3080433414 hasConceptScore W3080433414C127413603 @default.
- W3080433414 hasConceptScore W3080433414C134306372 @default.
- W3080433414 hasConceptScore W3080433414C154945302 @default.
- W3080433414 hasConceptScore W3080433414C15744967 @default.
- W3080433414 hasConceptScore W3080433414C177264268 @default.
- W3080433414 hasConceptScore W3080433414C199360897 @default.
- W3080433414 hasConceptScore W3080433414C201995342 @default.
- W3080433414 hasConceptScore W3080433414C2777212361 @default.
- W3080433414 hasConceptScore W3080433414C2780451532 @default.
- W3080433414 hasConceptScore W3080433414C2780767217 @default.
- W3080433414 hasConceptScore W3080433414C33923547 @default.
- W3080433414 hasConceptScore W3080433414C36503486 @default.
- W3080433414 hasConceptScore W3080433414C41008148 @default.