Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137138892> ?p ?o ?g. }
- W3137138892 abstract "Although the notion of task similarity is potentially interesting in a wide range of areas such as curriculum learning or automated planning, it has mostly been tied to transfer learning. Transfer is based on the idea of reusing the knowledge acquired in the learning of a set of source tasks to a new learning process in a target task, assuming that the target and source tasks are close enough. In recent years, transfer learning has succeeded in making Reinforcement Learning (RL) algorithms more efficient (e.g., by reducing the number of samples needed to achieve the (near-)optimal performance). Transfer in RL is based on the core concept of similarity: whenever the tasks are similar, the transferred knowledge can be reused to solve the target task and significantly improve the learning performance. Therefore, the selection of good metrics to measure these similarities is a critical aspect when building transfer RL algorithms, especially when this knowledge is transferred from simulation to the real world. In the literature, there are many metrics to measure the similarity between MDPs, hence, many definitions of similarity or its complement distance have been considered. In this paper, we propose a categorization of these metrics and analyze the definitions of similarity proposed so far, taking into account such categorization. We also follow this taxonomy to survey the existing literature, as well as suggesting future directions for the construction of new metrics." @default.
- W3137138892 created "2021-03-29" @default.
- W3137138892 creator A5004703726 @default.
- W3137138892 creator A5022896079 @default.
- W3137138892 creator A5051819167 @default.
- W3137138892 date "2021-03-08" @default.
- W3137138892 modified "2023-10-11" @default.
- W3137138892 title "A Taxonomy of Similarity Metrics for Markov Decision Processes." @default.
- W3137138892 cites W1534331386 @default.
- W3137138892 cites W1568835640 @default.
- W3137138892 cites W1573527757 @default.
- W3137138892 cites W1582256513 @default.
- W3137138892 cites W1974043469 @default.
- W3137138892 cites W1990600049 @default.
- W3137138892 cites W2096195880 @default.
- W3137138892 cites W2097381042 @default.
- W3137138892 cites W2099587183 @default.
- W3137138892 cites W2117831564 @default.
- W3137138892 cites W2126385963 @default.
- W3137138892 cites W2141559023 @default.
- W3137138892 cites W2158150115 @default.
- W3137138892 cites W2271262891 @default.
- W3137138892 cites W24272225 @default.
- W3137138892 cites W2464736835 @default.
- W3137138892 cites W2581240229 @default.
- W3137138892 cites W2760355785 @default.
- W3137138892 cites W2763323349 @default.
- W3137138892 cites W2808217720 @default.
- W3137138892 cites W2887462883 @default.
- W3137138892 cites W2997101648 @default.
- W3137138892 cites W3005639539 @default.
- W3137138892 cites W3011120880 @default.
- W3137138892 cites W3085438811 @default.
- W3137138892 cites W3121174195 @default.
- W3137138892 cites W867213644 @default.
- W3137138892 hasPublicationYear "2021" @default.
- W3137138892 type Work @default.
- W3137138892 sameAs 3137138892 @default.
- W3137138892 citedByCount "0" @default.
- W3137138892 crossrefType "posted-content" @default.
- W3137138892 hasAuthorship W3137138892A5004703726 @default.
- W3137138892 hasAuthorship W3137138892A5022896079 @default.
- W3137138892 hasAuthorship W3137138892A5051819167 @default.
- W3137138892 hasConcept C103278499 @default.
- W3137138892 hasConcept C105795698 @default.
- W3137138892 hasConcept C106189395 @default.
- W3137138892 hasConcept C115961682 @default.
- W3137138892 hasConcept C119857082 @default.
- W3137138892 hasConcept C150899416 @default.
- W3137138892 hasConcept C154945302 @default.
- W3137138892 hasConcept C159886148 @default.
- W3137138892 hasConcept C162324750 @default.
- W3137138892 hasConcept C177264268 @default.
- W3137138892 hasConcept C187736073 @default.
- W3137138892 hasConcept C18903297 @default.
- W3137138892 hasConcept C199360897 @default.
- W3137138892 hasConcept C206588197 @default.
- W3137138892 hasConcept C2776517306 @default.
- W3137138892 hasConcept C2780451532 @default.
- W3137138892 hasConcept C33923547 @default.
- W3137138892 hasConcept C41008148 @default.
- W3137138892 hasConcept C58642233 @default.
- W3137138892 hasConcept C59822182 @default.
- W3137138892 hasConcept C86803240 @default.
- W3137138892 hasConcept C94124525 @default.
- W3137138892 hasConcept C97541855 @default.
- W3137138892 hasConceptScore W3137138892C103278499 @default.
- W3137138892 hasConceptScore W3137138892C105795698 @default.
- W3137138892 hasConceptScore W3137138892C106189395 @default.
- W3137138892 hasConceptScore W3137138892C115961682 @default.
- W3137138892 hasConceptScore W3137138892C119857082 @default.
- W3137138892 hasConceptScore W3137138892C150899416 @default.
- W3137138892 hasConceptScore W3137138892C154945302 @default.
- W3137138892 hasConceptScore W3137138892C159886148 @default.
- W3137138892 hasConceptScore W3137138892C162324750 @default.
- W3137138892 hasConceptScore W3137138892C177264268 @default.
- W3137138892 hasConceptScore W3137138892C187736073 @default.
- W3137138892 hasConceptScore W3137138892C18903297 @default.
- W3137138892 hasConceptScore W3137138892C199360897 @default.
- W3137138892 hasConceptScore W3137138892C206588197 @default.
- W3137138892 hasConceptScore W3137138892C2776517306 @default.
- W3137138892 hasConceptScore W3137138892C2780451532 @default.
- W3137138892 hasConceptScore W3137138892C33923547 @default.
- W3137138892 hasConceptScore W3137138892C41008148 @default.
- W3137138892 hasConceptScore W3137138892C58642233 @default.
- W3137138892 hasConceptScore W3137138892C59822182 @default.
- W3137138892 hasConceptScore W3137138892C86803240 @default.
- W3137138892 hasConceptScore W3137138892C94124525 @default.
- W3137138892 hasConceptScore W3137138892C97541855 @default.
- W3137138892 hasLocation W31371388921 @default.
- W3137138892 hasOpenAccess W3137138892 @default.
- W3137138892 hasPrimaryLocation W31371388921 @default.
- W3137138892 hasRelatedWork W1981590391 @default.
- W3137138892 hasRelatedWork W1982643701 @default.
- W3137138892 hasRelatedWork W2078273977 @default.
- W3137138892 hasRelatedWork W2158757542 @default.
- W3137138892 hasRelatedWork W2581532568 @default.
- W3137138892 hasRelatedWork W2809755425 @default.
- W3137138892 hasRelatedWork W2896778177 @default.
- W3137138892 hasRelatedWork W2902659398 @default.