Matches in SemOpenAlex for { <https://semopenalex.org/work/W1556201700> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W1556201700 abstract "Usually in reinforcement learning, the goal of the agent is to maximize the expected return. However, in practical applications, algorithms that solely focus on maximizing the mean return could be inappropriate as they do not account for the variability of their solutions. Thereby, a variability measure could be included to accommodate for a risk-sensitive setting, i.e. where the system engineer can explicitly define the tolerated level of variance. Our approach is based on multi-objectivization where a standard single-objective environment is extended with one (or more) additional objectives. More precisely, we augment the standard feedback signal of an environment with an additional objective that defines the variance of the solution. We highlight that our algorithm, named risk-sensitive Pareto Q-learning, is (1) specifically tailored to learn a set of Pareto non-dominated policies that trade-off these two objectives. Additionally (2), the algorithm can also retrieve every policy that has been learned throughout the state-action space. This in contrast to standard risk-sensitive approaches where only a single trade-off between mean and variance is learned at a time." @default.
- W1556201700 created "2016-06-24" @default.
- W1556201700 creator A5064553018 @default.
- W1556201700 creator A5075504072 @default.
- W1556201700 creator A5084002137 @default.
- W1556201700 date "2015-05-01" @default.
- W1556201700 modified "2023-09-26" @default.
- W1556201700 title "Risk-sensitivity through multi-objective reinforcement learning" @default.
- W1556201700 cites W134786152 @default.
- W1556201700 cites W1539701879 @default.
- W1556201700 cites W1585711251 @default.
- W1556201700 cites W173958421 @default.
- W1556201700 cites W1833338034 @default.
- W1556201700 cites W1927597696 @default.
- W1556201700 cites W1965681731 @default.
- W1556201700 cites W2002305926 @default.
- W1556201700 cites W2050149892 @default.
- W1556201700 cites W2060248504 @default.
- W1556201700 cites W2060846151 @default.
- W1556201700 cites W2071279638 @default.
- W1556201700 cites W2113496026 @default.
- W1556201700 cites W2156578004 @default.
- W1556201700 cites W2157263597 @default.
- W1556201700 cites W2313791856 @default.
- W1556201700 cites W288089086 @default.
- W1556201700 cites W3106238320 @default.
- W1556201700 cites W4233696721 @default.
- W1556201700 cites W4248462665 @default.
- W1556201700 doi "https://doi.org/10.1109/cec.2015.7257098" @default.
- W1556201700 hasPublicationYear "2015" @default.
- W1556201700 type Work @default.
- W1556201700 sameAs 1556201700 @default.
- W1556201700 citedByCount "4" @default.
- W1556201700 countsByYear W15562017002016 @default.
- W1556201700 countsByYear W15562017002017 @default.
- W1556201700 countsByYear W15562017002021 @default.
- W1556201700 crossrefType "proceedings-article" @default.
- W1556201700 hasAuthorship W1556201700A5064553018 @default.
- W1556201700 hasAuthorship W1556201700A5075504072 @default.
- W1556201700 hasAuthorship W1556201700A5084002137 @default.
- W1556201700 hasConcept C119857082 @default.
- W1556201700 hasConcept C120665830 @default.
- W1556201700 hasConcept C121332964 @default.
- W1556201700 hasConcept C121955636 @default.
- W1556201700 hasConcept C126255220 @default.
- W1556201700 hasConcept C127413603 @default.
- W1556201700 hasConcept C137635306 @default.
- W1556201700 hasConcept C144133560 @default.
- W1556201700 hasConcept C154945302 @default.
- W1556201700 hasConcept C177264268 @default.
- W1556201700 hasConcept C192209626 @default.
- W1556201700 hasConcept C196083921 @default.
- W1556201700 hasConcept C199360897 @default.
- W1556201700 hasConcept C21200559 @default.
- W1556201700 hasConcept C24326235 @default.
- W1556201700 hasConcept C2776502983 @default.
- W1556201700 hasConcept C33923547 @default.
- W1556201700 hasConcept C41008148 @default.
- W1556201700 hasConcept C97541855 @default.
- W1556201700 hasConceptScore W1556201700C119857082 @default.
- W1556201700 hasConceptScore W1556201700C120665830 @default.
- W1556201700 hasConceptScore W1556201700C121332964 @default.
- W1556201700 hasConceptScore W1556201700C121955636 @default.
- W1556201700 hasConceptScore W1556201700C126255220 @default.
- W1556201700 hasConceptScore W1556201700C127413603 @default.
- W1556201700 hasConceptScore W1556201700C137635306 @default.
- W1556201700 hasConceptScore W1556201700C144133560 @default.
- W1556201700 hasConceptScore W1556201700C154945302 @default.
- W1556201700 hasConceptScore W1556201700C177264268 @default.
- W1556201700 hasConceptScore W1556201700C192209626 @default.
- W1556201700 hasConceptScore W1556201700C196083921 @default.
- W1556201700 hasConceptScore W1556201700C199360897 @default.
- W1556201700 hasConceptScore W1556201700C21200559 @default.
- W1556201700 hasConceptScore W1556201700C24326235 @default.
- W1556201700 hasConceptScore W1556201700C2776502983 @default.
- W1556201700 hasConceptScore W1556201700C33923547 @default.
- W1556201700 hasConceptScore W1556201700C41008148 @default.
- W1556201700 hasConceptScore W1556201700C97541855 @default.
- W1556201700 hasLocation W15562017001 @default.
- W1556201700 hasOpenAccess W1556201700 @default.
- W1556201700 hasPrimaryLocation W15562017001 @default.
- W1556201700 hasRelatedWork W1491338215 @default.
- W1556201700 hasRelatedWork W1493202049 @default.
- W1556201700 hasRelatedWork W1993518163 @default.
- W1556201700 hasRelatedWork W2025258469 @default.
- W1556201700 hasRelatedWork W2030465528 @default.
- W1556201700 hasRelatedWork W2058889384 @default.
- W1556201700 hasRelatedWork W2316613179 @default.
- W1556201700 hasRelatedWork W2961085424 @default.
- W1556201700 hasRelatedWork W4206669594 @default.
- W1556201700 hasRelatedWork W4319083788 @default.
- W1556201700 isParatext "false" @default.
- W1556201700 isRetracted "false" @default.
- W1556201700 magId "1556201700" @default.
- W1556201700 workType "article" @default.