Matches in SemOpenAlex for { <https://semopenalex.org/work/W2114199765> ?p ?o ?g. }
- W2114199765 abstract "We address the problem faced by an autonomous agent that must achieve quick responses to a family of qualitativelyrelated tasks, such as a robot interacting with different types of human participants. We work in the setting where the tasks share a state-action space and have the same qualitative objective but differ in the dynamics and reward process. We adopt a transfer approach where the agent attempts to exploit common structure in learnt policies to accelerate learning in a new one. Our technique consists of a few key steps. First, we use a probabilistic model to describe the regions in state space which successful trajectories seem to prefer. Then, we extract policy fragments from previously-learnt policies for these regions as candidates for reuse. These fragments may be treated as options with corresponding domains and termination conditions extracted by unsupervised learning. Then, the set of reusable policies is used when learning novel tasks, and the process repeats. The utility of this method is demonstrated through experiments in the simulated soccer domain, where the variability comes from the different possible behaviours of opponent teams, and the agent needs to perform well against novel opponents." @default.
- W2114199765 created "2016-06-24" @default.
- W2114199765 creator A5021151663 @default.
- W2114199765 creator A5071122608 @default.
- W2114199765 date "2013-03-15" @default.
- W2114199765 modified "2023-09-24" @default.
- W2114199765 title "Lifelong Learning of Structure in the Space of Policies" @default.
- W2114199765 cites W1492014007 @default.
- W2114199765 cites W1510402218 @default.
- W2114199765 cites W1523801836 @default.
- W2114199765 cites W1536990779 @default.
- W2114199765 cites W1556824961 @default.
- W2114199765 cites W1592847719 @default.
- W2114199765 cites W1598748993 @default.
- W2114199765 cites W1968768508 @default.
- W2114199765 cites W2031727428 @default.
- W2114199765 cites W2049633694 @default.
- W2114199765 cites W2097381042 @default.
- W2114199765 cites W2104641222 @default.
- W2114199765 cites W2109910161 @default.
- W2114199765 cites W2114451917 @default.
- W2114199765 cites W2132057084 @default.
- W2114199765 cites W2133853511 @default.
- W2114199765 cites W2145983895 @default.
- W2114199765 cites W2168640731 @default.
- W2114199765 cites W2169743339 @default.
- W2114199765 cites W2172131460 @default.
- W2114199765 cites W2188752309 @default.
- W2114199765 hasPublicationYear "2013" @default.
- W2114199765 type Work @default.
- W2114199765 sameAs 2114199765 @default.
- W2114199765 citedByCount "3" @default.
- W2114199765 countsByYear W21141997652014 @default.
- W2114199765 countsByYear W21141997652016 @default.
- W2114199765 countsByYear W21141997652017 @default.
- W2114199765 crossrefType "proceedings-article" @default.
- W2114199765 hasAuthorship W2114199765A5021151663 @default.
- W2114199765 hasAuthorship W2114199765A5071122608 @default.
- W2114199765 hasConcept C105795698 @default.
- W2114199765 hasConcept C107457646 @default.
- W2114199765 hasConcept C111919701 @default.
- W2114199765 hasConcept C119857082 @default.
- W2114199765 hasConcept C121332964 @default.
- W2114199765 hasConcept C127413603 @default.
- W2114199765 hasConcept C134306372 @default.
- W2114199765 hasConcept C13687954 @default.
- W2114199765 hasConcept C150899416 @default.
- W2114199765 hasConcept C154945302 @default.
- W2114199765 hasConcept C165696696 @default.
- W2114199765 hasConcept C177264268 @default.
- W2114199765 hasConcept C199360897 @default.
- W2114199765 hasConcept C206588197 @default.
- W2114199765 hasConcept C26517878 @default.
- W2114199765 hasConcept C2778572836 @default.
- W2114199765 hasConcept C2780791683 @default.
- W2114199765 hasConcept C33923547 @default.
- W2114199765 hasConcept C36503486 @default.
- W2114199765 hasConcept C38652104 @default.
- W2114199765 hasConcept C41008148 @default.
- W2114199765 hasConcept C41065033 @default.
- W2114199765 hasConcept C49937458 @default.
- W2114199765 hasConcept C548081761 @default.
- W2114199765 hasConcept C62520636 @default.
- W2114199765 hasConcept C72434380 @default.
- W2114199765 hasConcept C90509273 @default.
- W2114199765 hasConcept C98045186 @default.
- W2114199765 hasConceptScore W2114199765C105795698 @default.
- W2114199765 hasConceptScore W2114199765C107457646 @default.
- W2114199765 hasConceptScore W2114199765C111919701 @default.
- W2114199765 hasConceptScore W2114199765C119857082 @default.
- W2114199765 hasConceptScore W2114199765C121332964 @default.
- W2114199765 hasConceptScore W2114199765C127413603 @default.
- W2114199765 hasConceptScore W2114199765C134306372 @default.
- W2114199765 hasConceptScore W2114199765C13687954 @default.
- W2114199765 hasConceptScore W2114199765C150899416 @default.
- W2114199765 hasConceptScore W2114199765C154945302 @default.
- W2114199765 hasConceptScore W2114199765C165696696 @default.
- W2114199765 hasConceptScore W2114199765C177264268 @default.
- W2114199765 hasConceptScore W2114199765C199360897 @default.
- W2114199765 hasConceptScore W2114199765C206588197 @default.
- W2114199765 hasConceptScore W2114199765C26517878 @default.
- W2114199765 hasConceptScore W2114199765C2778572836 @default.
- W2114199765 hasConceptScore W2114199765C2780791683 @default.
- W2114199765 hasConceptScore W2114199765C33923547 @default.
- W2114199765 hasConceptScore W2114199765C36503486 @default.
- W2114199765 hasConceptScore W2114199765C38652104 @default.
- W2114199765 hasConceptScore W2114199765C41008148 @default.
- W2114199765 hasConceptScore W2114199765C41065033 @default.
- W2114199765 hasConceptScore W2114199765C49937458 @default.
- W2114199765 hasConceptScore W2114199765C548081761 @default.
- W2114199765 hasConceptScore W2114199765C62520636 @default.
- W2114199765 hasConceptScore W2114199765C72434380 @default.
- W2114199765 hasConceptScore W2114199765C90509273 @default.
- W2114199765 hasConceptScore W2114199765C98045186 @default.
- W2114199765 hasLocation W21141997651 @default.
- W2114199765 hasOpenAccess W2114199765 @default.
- W2114199765 hasPrimaryLocation W21141997651 @default.
- W2114199765 hasRelatedWork W1993647444 @default.
- W2114199765 hasRelatedWork W2005043268 @default.
- W2114199765 hasRelatedWork W2064763705 @default.