Matches in SemOpenAlex for { <https://semopenalex.org/work/W1967859677> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W1967859677 abstract "Most experiments on policy search for robotics focus on isolated tasks, where the experiment is split into two distinct phases: (1) the learning phase, where the robot learns the task through exploration; (2) the exploitation phase, where exploration is turned off, and the robot demonstrates its performance on the task it has learned. In this paper, we present an algorithm that enables robots to continually and autonomously alternate between these phases. We do so by combining the `Policy Improvement with Path Integrals' direct reinforcement learning algorithm with the covariance matrix adaptation rule from the `Cross-Entropy Method' optimization algorithm. This integration is possible because both algorithms iteratively update parameters with probability-weighted averaging. A practical advantage of the novel algorithm, called PI2-CMA, is that it alleviates the user from having to manually tune the degree of exploration. We evaluate PI2-CMA's ability to continually and autonomously tune exploration on two tasks." @default.
- W1967859677 created "2016-06-24" @default.
- W1967859677 creator A5017689065 @default.
- W1967859677 date "2012-10-01" @default.
- W1967859677 modified "2023-10-17" @default.
- W1967859677 title "Adaptive exploration for continual reinforcement learning" @default.
- W1967859677 cites W1505937442 @default.
- W1967859677 cites W2012392077 @default.
- W1967859677 cites W2119717200 @default.
- W1967859677 cites W2168921921 @default.
- W1967859677 cites W2172968643 @default.
- W1967859677 cites W2489939061 @default.
- W1967859677 doi "https://doi.org/10.1109/iros.2012.6385818" @default.
- W1967859677 hasPublicationYear "2012" @default.
- W1967859677 type Work @default.
- W1967859677 sameAs 1967859677 @default.
- W1967859677 citedByCount "12" @default.
- W1967859677 countsByYear W19678596772012 @default.
- W1967859677 countsByYear W19678596772013 @default.
- W1967859677 countsByYear W19678596772014 @default.
- W1967859677 countsByYear W19678596772016 @default.
- W1967859677 countsByYear W19678596772017 @default.
- W1967859677 countsByYear W19678596772018 @default.
- W1967859677 countsByYear W19678596772019 @default.
- W1967859677 countsByYear W19678596772021 @default.
- W1967859677 countsByYear W19678596772023 @default.
- W1967859677 crossrefType "proceedings-article" @default.
- W1967859677 hasAuthorship W1967859677A5017689065 @default.
- W1967859677 hasConcept C106301342 @default.
- W1967859677 hasConcept C119857082 @default.
- W1967859677 hasConcept C120665830 @default.
- W1967859677 hasConcept C121332964 @default.
- W1967859677 hasConcept C127413603 @default.
- W1967859677 hasConcept C139807058 @default.
- W1967859677 hasConcept C154945302 @default.
- W1967859677 hasConcept C159149176 @default.
- W1967859677 hasConcept C192209626 @default.
- W1967859677 hasConcept C201995342 @default.
- W1967859677 hasConcept C205555498 @default.
- W1967859677 hasConcept C207002847 @default.
- W1967859677 hasConcept C2780451532 @default.
- W1967859677 hasConcept C34413123 @default.
- W1967859677 hasConcept C41008148 @default.
- W1967859677 hasConcept C62520636 @default.
- W1967859677 hasConcept C81074085 @default.
- W1967859677 hasConcept C90509273 @default.
- W1967859677 hasConcept C97541855 @default.
- W1967859677 hasConceptScore W1967859677C106301342 @default.
- W1967859677 hasConceptScore W1967859677C119857082 @default.
- W1967859677 hasConceptScore W1967859677C120665830 @default.
- W1967859677 hasConceptScore W1967859677C121332964 @default.
- W1967859677 hasConceptScore W1967859677C127413603 @default.
- W1967859677 hasConceptScore W1967859677C139807058 @default.
- W1967859677 hasConceptScore W1967859677C154945302 @default.
- W1967859677 hasConceptScore W1967859677C159149176 @default.
- W1967859677 hasConceptScore W1967859677C192209626 @default.
- W1967859677 hasConceptScore W1967859677C201995342 @default.
- W1967859677 hasConceptScore W1967859677C205555498 @default.
- W1967859677 hasConceptScore W1967859677C207002847 @default.
- W1967859677 hasConceptScore W1967859677C2780451532 @default.
- W1967859677 hasConceptScore W1967859677C34413123 @default.
- W1967859677 hasConceptScore W1967859677C41008148 @default.
- W1967859677 hasConceptScore W1967859677C62520636 @default.
- W1967859677 hasConceptScore W1967859677C81074085 @default.
- W1967859677 hasConceptScore W1967859677C90509273 @default.
- W1967859677 hasConceptScore W1967859677C97541855 @default.
- W1967859677 hasLocation W19678596771 @default.
- W1967859677 hasLocation W19678596772 @default.
- W1967859677 hasOpenAccess W1967859677 @default.
- W1967859677 hasPrimaryLocation W19678596771 @default.
- W1967859677 hasRelatedWork W1537644361 @default.
- W1967859677 hasRelatedWork W2044116962 @default.
- W1967859677 hasRelatedWork W2048993376 @default.
- W1967859677 hasRelatedWork W2066251678 @default.
- W1967859677 hasRelatedWork W2078341713 @default.
- W1967859677 hasRelatedWork W2137642139 @default.
- W1967859677 hasRelatedWork W2972973372 @default.
- W1967859677 hasRelatedWork W4283641297 @default.
- W1967859677 hasRelatedWork W4319083788 @default.
- W1967859677 hasRelatedWork W2182407375 @default.
- W1967859677 isParatext "false" @default.
- W1967859677 isRetracted "false" @default.
- W1967859677 magId "1967859677" @default.
- W1967859677 workType "article" @default.