FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2058324982> ?p ?o ?g. }

• W2058324982 abstract "Utility theory has served as a bedrock for modeling risk in economics. Where risk is involved in decision-making, for solving Markov decision processes (MDPs) via utility theory, the exponential utility (EU) function has been used in the literature as an objective function for capturing risk-averse behavior. The EU function framework uses a so-called risk-averseness coefficient (RAC) that seeks to quantify the risk appetite of the decision-maker. Unfortunately, as we show in this paper, the EU framework suffers from computational deficiencies that prevent it from being useful in practice for solution methods based on reinforcement learning (RL). In particular, the value function becomes very large and typically the computer overflows. We provide a simple example to demonstrate this. Further, we show empirically how a variance-adjusted (VA) approach, which approximates the EU function objective for reasonable values of the RAC, can be used in the RL algorithm. The VA framework in a sense has two objectives: maximize expected returns and minimize variance. We conduct empirical studies on a VA-based RL algorithm on the semi-MDP (SMDP), which is a more general version of the MDP. We conclude with a mathematical proof of the boundedness of the iterates in our algorithm." @default.
• W2058324982 created "2016-06-24" @default.
• W2058324982 creator A5028388499 @default.
• W2058324982 creator A5053889549 @default.
• W2058324982 creator A5083526451 @default.
• W2058324982 date "2014-12-01" @default.
• W2058324982 modified "2023-09-27" @default.
• W2058324982 title "Beyond exponential utility functions: A variance-adjusted approach for risk-averse reinforcement learning" @default.
• W2058324982 cites W129373126 @default.
• W2058324982 cites W134786152 @default.
• W2058324982 cites W1534175858 @default.
• W2058324982 cites W1557760016 @default.
• W2058324982 cites W1576452626 @default.
• W2058324982 cites W1585575029 @default.
• W2058324982 cites W1589395967 @default.
• W2058324982 cites W1626155273 @default.
• W2058324982 cites W1980079915 @default.
• W2058324982 cites W1997933673 @default.
• W2058324982 cites W1998645260 @default.
• W2058324982 cites W2001009060 @default.
• W2058324982 cites W2021693949 @default.
• W2058324982 cites W2024928738 @default.
• W2058324982 cites W2036694592 @default.
• W2058324982 cites W2057510529 @default.
• W2058324982 cites W2077343054 @default.
• W2058324982 cites W2088413745 @default.
• W2058324982 cites W2098432798 @default.
• W2058324982 cites W2100353677 @default.
• W2058324982 cites W2107289230 @default.
• W2058324982 cites W2124684414 @default.
• W2058324982 cites W2128661050 @default.
• W2058324982 cites W2139914196 @default.
• W2058324982 cites W2173945562 @default.
• W2058324982 cites W2505159842 @default.
• W2058324982 cites W2911283634 @default.
• W2058324982 cites W2914656440 @default.
• W2058324982 cites W3022853033 @default.
• W2058324982 cites W3124527335 @default.
• W2058324982 cites W3139984405 @default.
• W2058324982 cites W3147321350 @default.
• W2058324982 cites W3122210430 @default.
• W2058324982 doi "https://doi.org/10.1109/adprl.2014.7010645" @default.
• W2058324982 hasPublicationYear "2014" @default.
• W2058324982 type Work @default.
• W2058324982 sameAs 2058324982 @default.
• W2058324982 citedByCount "4" @default.
• W2058324982 countsByYear W20583249822016 @default.
• W2058324982 countsByYear W20583249822019 @default.
• W2058324982 countsByYear W20583249822020 @default.
• W2058324982 crossrefType "proceedings-article" @default.
• W2058324982 hasAuthorship W2058324982A5028388499 @default.
• W2058324982 hasAuthorship W2058324982A5053889549 @default.
• W2058324982 hasAuthorship W2058324982A5083526451 @default.
• W2058324982 hasConcept C105795698 @default.
• W2058324982 hasConcept C106189395 @default.
• W2058324982 hasConcept C121955636 @default.
• W2058324982 hasConcept C126255220 @default.
• W2058324982 hasConcept C134306372 @default.
• W2058324982 hasConcept C14036430 @default.
• W2058324982 hasConcept C140479938 @default.
• W2058324982 hasConcept C144237770 @default.
• W2058324982 hasConcept C14646407 @default.
• W2058324982 hasConcept C151376022 @default.
• W2058324982 hasConcept C154945302 @default.
• W2058324982 hasConcept C159886148 @default.
• W2058324982 hasConcept C162324750 @default.
• W2058324982 hasConcept C188116033 @default.
• W2058324982 hasConcept C196083921 @default.
• W2058324982 hasConcept C205706631 @default.
• W2058324982 hasConcept C2779449553 @default.
• W2058324982 hasConcept C33923547 @default.
• W2058324982 hasConcept C41008148 @default.
• W2058324982 hasConcept C78458016 @default.
• W2058324982 hasConcept C86803240 @default.
• W2058324982 hasConcept C97541855 @default.
• W2058324982 hasConceptScore W2058324982C105795698 @default.
• W2058324982 hasConceptScore W2058324982C106189395 @default.
• W2058324982 hasConceptScore W2058324982C121955636 @default.
• W2058324982 hasConceptScore W2058324982C126255220 @default.
• W2058324982 hasConceptScore W2058324982C134306372 @default.
• W2058324982 hasConceptScore W2058324982C14036430 @default.
• W2058324982 hasConceptScore W2058324982C140479938 @default.
• W2058324982 hasConceptScore W2058324982C144237770 @default.
• W2058324982 hasConceptScore W2058324982C14646407 @default.
• W2058324982 hasConceptScore W2058324982C151376022 @default.
• W2058324982 hasConceptScore W2058324982C154945302 @default.
• W2058324982 hasConceptScore W2058324982C159886148 @default.
• W2058324982 hasConceptScore W2058324982C162324750 @default.
• W2058324982 hasConceptScore W2058324982C188116033 @default.
• W2058324982 hasConceptScore W2058324982C196083921 @default.
• W2058324982 hasConceptScore W2058324982C205706631 @default.
• W2058324982 hasConceptScore W2058324982C2779449553 @default.
• W2058324982 hasConceptScore W2058324982C33923547 @default.
• W2058324982 hasConceptScore W2058324982C41008148 @default.
• W2058324982 hasConceptScore W2058324982C78458016 @default.
• W2058324982 hasConceptScore W2058324982C86803240 @default.
• W2058324982 hasConceptScore W2058324982C97541855 @default.
• W2058324982 hasLocation W20583249821 @default.
• W2058324982 hasOpenAccess W2058324982 @default.
• W2058324982 hasPrimaryLocation W20583249821 @default.

• next