FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2004303440> ?p ?o ?g. }

• W2004303440 endingPage "73" @default.
• W2004303440 startingPage "49" @default.
• W2004303440 abstract "We introduce the Self-Adaptive Goal Generation - Robust Intelligent Adaptive Curiosity (SAGG-RIAC) architecture as an intrinsi- cally motivated goal exploration mechanism which allows active learning of inverse models in high-dimensional redundant robots. This allows a robot to efficiently and actively learn distributions of parameterized motor skills/policies that solve a corresponding distribution of parameterized tasks/goals. The architecture makes the robot sample actively novel parameterized tasks in the task space, based on a measure of competence progress, each of which triggers low-level goal-directed learning of the motor policy pa- rameters that allow to solve it. For both learning and generalization, the system leverages regression techniques which allow to infer the motor policy parameters corresponding to a given novel parameterized task, and based on the previously learnt correspondences between policy and task parameters. We present experiments with high-dimensional continuous sensorimotor spaces in three different robotic setups: 1) learning the inverse kinematics in a highly-redundant robotic arm, 2) learning omnidirectional locomotion with motor primitives in a quadruped robot, 3) an arm learning to control a fishing rod with a flexible wire. We show that 1) exploration in the task space can be a lot faster than exploration in the actuator space for learning inverse models in redundant robots; 2) selecting goals maximizing competence progress creates developmental trajectories driving the robot to progressively focus on tasks of increasing complexity and is statistically significantly more efficient than selecting tasks randomly, as well as more efficient than different standard active motor babbling methods; 3) this architecture allows the robot to actively discover which parts of its task space it can learn to reach and which part it cannot." @default.
• W2004303440 created "2016-06-24" @default.
• W2004303440 creator A5080846930 @default.
• W2004303440 creator A5085903884 @default.
• W2004303440 date "2013-01-01" @default.
• W2004303440 modified "2023-10-15" @default.
• W2004303440 title "Active learning of inverse models with intrinsically motivated goal exploration in robots" @default.
• W2004303440 cites W1491843047 @default.
• W2004303440 cites W1510052597 @default.
• W2004303440 cites W1528361845 @default.
• W2004303440 cites W1562462135 @default.
• W2004303440 cites W1863227302 @default.
• W2004303440 cites W1963656947 @default.
• W2004303440 cites W1963964947 @default.
• W2004303440 cites W1966134828 @default.
• W2004303440 cites W1972837991 @default.
• W2004303440 cites W1976606095 @default.
• W2004303440 cites W1989616852 @default.
• W2004303440 cites W1991247894 @default.
• W2004303440 cites W1997543377 @default.
• W2004303440 cites W2000514530 @default.
• W2004303440 cites W2006228990 @default.
• W2004303440 cites W2008026620 @default.
• W2004303440 cites W2012479417 @default.
• W2004303440 cites W2021367230 @default.
• W2004303440 cites W2021774297 @default.
• W2004303440 cites W2031539092 @default.
• W2004303440 cites W2034806191 @default.
• W2004303440 cites W2034891032 @default.
• W2004303440 cites W2050624087 @default.
• W2004303440 cites W2052729098 @default.
• W2004303440 cites W2061868368 @default.
• W2004303440 cites W2063978650 @default.
• W2004303440 cites W2074200719 @default.
• W2004303440 cites W2075670547 @default.
• W2004303440 cites W2082288587 @default.
• W2004303440 cites W2096649264 @default.
• W2004303440 cites W2100159492 @default.
• W2004303440 cites W2101524054 @default.
• W2004303440 cites W2102484448 @default.
• W2004303440 cites W2109572794 @default.
• W2004303440 cites W2111656597 @default.
• W2004303440 cites W2112036188 @default.
• W2004303440 cites W2113260111 @default.
• W2004303440 cites W2114524506 @default.
• W2004303440 cites W2116086091 @default.
• W2004303440 cites W2117726420 @default.
• W2004303440 cites W2127412976 @default.
• W2004303440 cites W2132335923 @default.
• W2004303440 cites W2132736959 @default.
• W2004303440 cites W2137674828 @default.
• W2004303440 cites W2140539195 @default.
• W2004303440 cites W2144105913 @default.
• W2004303440 cites W2144741745 @default.
• W2004303440 cites W2145932718 @default.
• W2004303440 cites W2147501341 @default.
• W2004303440 cites W2147804103 @default.
• W2004303440 cites W2150012741 @default.
• W2004303440 cites W2151834591 @default.
• W2004303440 cites W2154018708 @default.
• W2004303440 cites W2155352776 @default.
• W2004303440 cites W2156163138 @default.
• W2004303440 cites W2156174987 @default.
• W2004303440 cites W2157720571 @default.
• W2004303440 cites W2162951026 @default.
• W2004303440 cites W2164424353 @default.
• W2004303440 cites W2168772674 @default.
• W2004303440 cites W2170156068 @default.
• W2004303440 cites W2170899200 @default.
• W2004303440 cites W2172968643 @default.
• W2004303440 cites W2334207126 @default.
• W2004303440 cites W2427881153 @default.
• W2004303440 cites W2591436094 @default.
• W2004303440 cites W2597661640 @default.
• W2004303440 cites W2896027395 @default.
• W2004303440 cites W2949071206 @default.
• W2004303440 cites W3100911534 @default.
• W2004303440 cites W3139574508 @default.
• W2004303440 cites W4230030242 @default.
• W2004303440 doi "https://doi.org/10.1016/j.robot.2012.05.008" @default.
• W2004303440 hasPublicationYear "2013" @default.
• W2004303440 type Work @default.
• W2004303440 sameAs 2004303440 @default.
• W2004303440 citedByCount "313" @default.
• W2004303440 countsByYear W20043034402012 @default.
• W2004303440 countsByYear W20043034402013 @default.
• W2004303440 countsByYear W20043034402014 @default.
• W2004303440 countsByYear W20043034402015 @default.
• W2004303440 countsByYear W20043034402016 @default.
• W2004303440 countsByYear W20043034402017 @default.
• W2004303440 countsByYear W20043034402018 @default.
• W2004303440 countsByYear W20043034402019 @default.
• W2004303440 countsByYear W20043034402020 @default.
• W2004303440 countsByYear W20043034402021 @default.
• W2004303440 countsByYear W20043034402022 @default.
• W2004303440 countsByYear W20043034402023 @default.
• W2004303440 crossrefType "journal-article" @default.
• W2004303440 hasAuthorship W2004303440A5080846930 @default.

• next