FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3172100893> ?p ?o ?g. }

• W3172100893 abstract "Real world tasks, in homes or other unstructured environments, require interacting with objects (including people) and understanding the variety of physical relationships between them. For example, choosing where to place a fork at a table requires knowing the correct position and orientation relative to the plate. Further, the quantity of objects and the roles they play might change from one occasion to the next; the variables are not fixed and predefined. For an intelligent agent to navigate this complex space, it needs to be able to identify and focus on just those variables that are relevant. Also, if a robot or other artificial agent can learn such physical relations from its own experience in a task, it can save manual engineering effort and automatically adapt to new situations.Relational learning, while often focused on discrete domains, applies to situations with arbitrary numbers of objects by using existential and/or universal quantifiers from first-order logic. The field of reinforcement learning (RL) addresses learning task execution from scalar rewards based on agent state and action. Relational reinforcement learning (RRL) combines these two fields.In this dissertation, I present an RRL technique emphasizing relations that are merely implicit in multidimensional, continuous object attributes, such as position, color, and size. This technique requires analyzing permutations of possible object comparisons while simultaneously working in the multidimensional spaces defined by their attributes. Existing similar RRL methods query only one dimension at a time, which limits effectiveness when multiple dimensions are correlated.Specifically, I present a representation policy iteration (RPI) method using the spatiotemporal multidimensional relational framework (SMRF) for learning relational decision trees from object attributes. This SMRF-RPI algorithm interleaves the learning of relational representations and of policies for agent action. Further, SMRF-RPI includes support for continuous actions. As a component of the SMRF framework, I also present a novel multiple instance learning (MIL) algorithm, which is able to learn parametric, existential decision volumes within a feature space in a robust manner.Finally, I demonstrate SMRF-RPI on a variety of developmentally motivated blocks world tasks, as well as effective transfer and sample efficient learning in a standard keepaway soccer benchmark task. Both domains involve complicated, simulated world dynamics in continuous space. These experiments demonstrate SMRF-RPI as a promising method for applying RRL techniques in multidimensional, continuous domains." @default.
• W3172100893 created "2021-06-22" @default.
• W3172100893 creator A5065575387 @default.
• W3172100893 date "2015-01-01" @default.
• W3172100893 modified "2023-09-27" @default.
• W3172100893 title "Learning Action-State Representation Forests for Implicitly Relational Worlds" @default.
• W3172100893 hasPublicationYear "2015" @default.
• W3172100893 type Work @default.
• W3172100893 sameAs 3172100893 @default.
• W3172100893 citedByCount "0" @default.
• W3172100893 crossrefType "journal-article" @default.
• W3172100893 hasAuthorship W3172100893A5065575387 @default.
• W3172100893 hasConcept C121332964 @default.
• W3172100893 hasConcept C124101348 @default.
• W3172100893 hasConcept C136197465 @default.
• W3172100893 hasConcept C154945302 @default.
• W3172100893 hasConcept C162324750 @default.
• W3172100893 hasConcept C17744445 @default.
• W3172100893 hasConcept C177877439 @default.
• W3172100893 hasConcept C187736073 @default.
• W3172100893 hasConcept C199539241 @default.
• W3172100893 hasConcept C202444582 @default.
• W3172100893 hasConcept C2776359362 @default.
• W3172100893 hasConcept C2780451532 @default.
• W3172100893 hasConcept C2780791683 @default.
• W3172100893 hasConcept C2781238097 @default.
• W3172100893 hasConcept C33676613 @default.
• W3172100893 hasConcept C33923547 @default.
• W3172100893 hasConcept C41008148 @default.
• W3172100893 hasConcept C5655090 @default.
• W3172100893 hasConcept C62520636 @default.
• W3172100893 hasConcept C94625758 @default.
• W3172100893 hasConcept C9652623 @default.
• W3172100893 hasConcept C97541855 @default.
• W3172100893 hasConceptScore W3172100893C121332964 @default.
• W3172100893 hasConceptScore W3172100893C124101348 @default.
• W3172100893 hasConceptScore W3172100893C136197465 @default.
• W3172100893 hasConceptScore W3172100893C154945302 @default.
• W3172100893 hasConceptScore W3172100893C162324750 @default.
• W3172100893 hasConceptScore W3172100893C17744445 @default.
• W3172100893 hasConceptScore W3172100893C177877439 @default.
• W3172100893 hasConceptScore W3172100893C187736073 @default.
• W3172100893 hasConceptScore W3172100893C199539241 @default.
• W3172100893 hasConceptScore W3172100893C202444582 @default.
• W3172100893 hasConceptScore W3172100893C2776359362 @default.
• W3172100893 hasConceptScore W3172100893C2780451532 @default.
• W3172100893 hasConceptScore W3172100893C2780791683 @default.
• W3172100893 hasConceptScore W3172100893C2781238097 @default.
• W3172100893 hasConceptScore W3172100893C33676613 @default.
• W3172100893 hasConceptScore W3172100893C33923547 @default.
• W3172100893 hasConceptScore W3172100893C41008148 @default.
• W3172100893 hasConceptScore W3172100893C5655090 @default.
• W3172100893 hasConceptScore W3172100893C62520636 @default.
• W3172100893 hasConceptScore W3172100893C94625758 @default.
• W3172100893 hasConceptScore W3172100893C9652623 @default.
• W3172100893 hasConceptScore W3172100893C97541855 @default.
• W3172100893 hasLocation W31721008931 @default.
• W3172100893 hasOpenAccess W3172100893 @default.
• W3172100893 hasPrimaryLocation W31721008931 @default.
• W3172100893 hasRelatedWork W189652262 @default.
• W3172100893 hasRelatedWork W191985209 @default.
• W3172100893 hasRelatedWork W1990654808 @default.
• W3172100893 hasRelatedWork W2133001472 @default.
• W3172100893 hasRelatedWork W2270835334 @default.
• W3172100893 hasRelatedWork W2294805292 @default.
• W3172100893 hasRelatedWork W2402540331 @default.
• W3172100893 hasRelatedWork W2523124567 @default.
• W3172100893 hasRelatedWork W2752112706 @default.
• W3172100893 hasRelatedWork W2887503931 @default.
• W3172100893 hasRelatedWork W2963240617 @default.
• W3172100893 hasRelatedWork W2963241167 @default.
• W3172100893 hasRelatedWork W2965015991 @default.
• W3172100893 hasRelatedWork W298069310 @default.
• W3172100893 hasRelatedWork W2989941899 @default.
• W3172100893 hasRelatedWork W3035041226 @default.
• W3172100893 hasRelatedWork W3106081758 @default.
• W3172100893 hasRelatedWork W3126596751 @default.
• W3172100893 hasRelatedWork W3166342932 @default.
• W3172100893 hasRelatedWork W3183773282 @default.
• W3172100893 isParatext "false" @default.
• W3172100893 isRetracted "false" @default.
• W3172100893 magId "3172100893" @default.
• W3172100893 workType "article" @default.