Matches in SemOpenAlex for { <https://semopenalex.org/work/W2064763705> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2064763705 abstract "One of the challenges for artificial agents is managing the complexity of their environment and task domain as they learn increasingly difficult tasks. This is especially true of agents that are grounded in the physical world, which contains a vast number of features and potentially very complex dynamics. A scalable solution to this problem in terms of forming, managing, and re-using compact, grounded representations in order to address the state explosion problem is thus a prerequisite of physically grounded, agent-based systems that can apply their past experience to new tasks and communicate that experience with other agents. To achieve this, it is essential that agents can form conceptual features that are relevant for and re-usable in their task domain without outside intervention and that these agents can effectively focus their attention on only the relevant features and concepts for the task at hand. This paper presents a framework for managing state complexity by automatically constructing abstract, symbolic features which encode important, task and domain-relevant properties and partition the raw feature space such that the agent need only consider a compressed view of the environment when learning new tasks. To exploit this, the framework during learning of new tasks uses U-Trees to construct minimal feature sets and thus compact state representations for these new tasks, allowing for potentially significant improvements in learning times." @default.
- W2064763705 created "2016-06-24" @default.
- W2064763705 creator A5034782991 @default.
- W2064763705 creator A5047174917 @default.
- W2064763705 date "2012-10-01" @default.
- W2064763705 modified "2023-10-14" @default.
- W2064763705 title "Symbol generation and feature selection for reinforcement learning agents using affordances and U-Trees" @default.
- W2064763705 cites W1534331386 @default.
- W2064763705 cites W1592847719 @default.
- W2064763705 cites W1666476 @default.
- W2064763705 cites W2109910161 @default.
- W2064763705 cites W2114451917 @default.
- W2064763705 cites W2143435603 @default.
- W2064763705 cites W2158150115 @default.
- W2064763705 cites W2217910170 @default.
- W2064763705 cites W2548352678 @default.
- W2064763705 cites W3011120880 @default.
- W2064763705 cites W3139460557 @default.
- W2064763705 doi "https://doi.org/10.1109/icsmc.2012.6377801" @default.
- W2064763705 hasPublicationYear "2012" @default.
- W2064763705 type Work @default.
- W2064763705 sameAs 2064763705 @default.
- W2064763705 citedByCount "1" @default.
- W2064763705 countsByYear W20647637052017 @default.
- W2064763705 crossrefType "proceedings-article" @default.
- W2064763705 hasAuthorship W2064763705A5034782991 @default.
- W2064763705 hasAuthorship W2064763705A5047174917 @default.
- W2064763705 hasConcept C107457646 @default.
- W2064763705 hasConcept C134306372 @default.
- W2064763705 hasConcept C138885662 @default.
- W2064763705 hasConcept C154945302 @default.
- W2064763705 hasConcept C165696696 @default.
- W2064763705 hasConcept C194995250 @default.
- W2064763705 hasConcept C199360897 @default.
- W2064763705 hasConcept C2776401178 @default.
- W2064763705 hasConcept C2780801425 @default.
- W2064763705 hasConcept C33923547 @default.
- W2064763705 hasConcept C36503486 @default.
- W2064763705 hasConcept C38652104 @default.
- W2064763705 hasConcept C41008148 @default.
- W2064763705 hasConcept C41895202 @default.
- W2064763705 hasConcept C97541855 @default.
- W2064763705 hasConceptScore W2064763705C107457646 @default.
- W2064763705 hasConceptScore W2064763705C134306372 @default.
- W2064763705 hasConceptScore W2064763705C138885662 @default.
- W2064763705 hasConceptScore W2064763705C154945302 @default.
- W2064763705 hasConceptScore W2064763705C165696696 @default.
- W2064763705 hasConceptScore W2064763705C194995250 @default.
- W2064763705 hasConceptScore W2064763705C199360897 @default.
- W2064763705 hasConceptScore W2064763705C2776401178 @default.
- W2064763705 hasConceptScore W2064763705C2780801425 @default.
- W2064763705 hasConceptScore W2064763705C33923547 @default.
- W2064763705 hasConceptScore W2064763705C36503486 @default.
- W2064763705 hasConceptScore W2064763705C38652104 @default.
- W2064763705 hasConceptScore W2064763705C41008148 @default.
- W2064763705 hasConceptScore W2064763705C41895202 @default.
- W2064763705 hasConceptScore W2064763705C97541855 @default.
- W2064763705 hasLocation W20647637051 @default.
- W2064763705 hasOpenAccess W2064763705 @default.
- W2064763705 hasPrimaryLocation W20647637051 @default.
- W2064763705 hasRelatedWork W2045445342 @default.
- W2064763705 hasRelatedWork W207752401 @default.
- W2064763705 hasRelatedWork W2083432852 @default.
- W2064763705 hasRelatedWork W2211596958 @default.
- W2064763705 hasRelatedWork W2256638296 @default.
- W2064763705 hasRelatedWork W2621131026 @default.
- W2064763705 hasRelatedWork W2963431633 @default.
- W2064763705 hasRelatedWork W2964604098 @default.
- W2064763705 hasRelatedWork W3008081459 @default.
- W2064763705 hasRelatedWork W2188875124 @default.
- W2064763705 isParatext "false" @default.
- W2064763705 isRetracted "false" @default.
- W2064763705 magId "2064763705" @default.
- W2064763705 workType "article" @default.