Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285403797> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4285403797 endingPage "103765" @default.
- W4285403797 startingPage "103765" @default.
- W4285403797 abstract "Keeping risk under control is a primary objective in many critical real-world domains, including finance and healthcare. The literature on risk-averse reinforcement learning (RL) has mostly focused on designing ad-hoc algorithms for specific risk measures. As such, most of these algorithms do not easily generalize to measures other than the one they are designed for. Furthermore, it is often unclear whether state-of-the-art risk-neutral RL algorithms can be extended to reduce risk. In this paper, we take a step towards overcoming these limitations, proposing a single framework to optimize some of the most popular risk measures, including conditional value-at-risk, utility functions, and mean-variance. Leveraging recent theoretical results on state augmentation, we transform the decision-making process so that optimizing the chosen risk measure in the original environment is equivalent to optimizing the expected cost in the transformed one. We then present a simple risk-sensitive meta-algorithm that transforms the trajectories it collects from the environment and feeds these into any risk-neutral policy optimization method. Finally, we provide extensive experiments that show the benefits of our approach over existing ad-hoc methodologies in different domains, including the Mujoco robotic suite and a real-world trading dataset." @default.
- W4285403797 created "2022-07-14" @default.
- W4285403797 creator A5015216456 @default.
- W4285403797 creator A5017130830 @default.
- W4285403797 creator A5024686404 @default.
- W4285403797 creator A5025172054 @default.
- W4285403797 creator A5063839691 @default.
- W4285403797 creator A5066485895 @default.
- W4285403797 date "2022-10-01" @default.
- W4285403797 modified "2023-09-29" @default.
- W4285403797 title "Risk-averse policy optimization via risk-neutral policy optimization" @default.
- W4285403797 cites W1540764732 @default.
- W4285403797 cites W1585575029 @default.
- W4285403797 cites W1647779468 @default.
- W4285403797 cites W1965878388 @default.
- W4285403797 cites W1977655452 @default.
- W4285403797 cites W2000769684 @default.
- W4285403797 cites W2019291268 @default.
- W4285403797 cites W2023901033 @default.
- W4285403797 cites W2027106436 @default.
- W4285403797 cites W2086304253 @default.
- W4285403797 cites W2088413745 @default.
- W4285403797 cites W2094177537 @default.
- W4285403797 cites W2113913482 @default.
- W4285403797 cites W2119717200 @default.
- W4285403797 cites W2139914196 @default.
- W4285403797 cites W2145339207 @default.
- W4285403797 cites W2155153696 @default.
- W4285403797 cites W2160769068 @default.
- W4285403797 cites W2169015875 @default.
- W4285403797 cites W2257979135 @default.
- W4285403797 cites W3027406032 @default.
- W4285403797 cites W3103182070 @default.
- W4285403797 doi "https://doi.org/10.1016/j.artint.2022.103765" @default.
- W4285403797 hasPublicationYear "2022" @default.
- W4285403797 type Work @default.
- W4285403797 citedByCount "2" @default.
- W4285403797 countsByYear W42854037972023 @default.
- W4285403797 crossrefType "journal-article" @default.
- W4285403797 hasAuthorship W4285403797A5015216456 @default.
- W4285403797 hasAuthorship W4285403797A5017130830 @default.
- W4285403797 hasAuthorship W4285403797A5024686404 @default.
- W4285403797 hasAuthorship W4285403797A5025172054 @default.
- W4285403797 hasAuthorship W4285403797A5063839691 @default.
- W4285403797 hasAuthorship W4285403797A5066485895 @default.
- W4285403797 hasConcept C111919701 @default.
- W4285403797 hasConcept C121955636 @default.
- W4285403797 hasConcept C126255220 @default.
- W4285403797 hasConcept C154945302 @default.
- W4285403797 hasConcept C162324750 @default.
- W4285403797 hasConcept C166957645 @default.
- W4285403797 hasConcept C196083921 @default.
- W4285403797 hasConcept C33923547 @default.
- W4285403797 hasConcept C41008148 @default.
- W4285403797 hasConcept C79581498 @default.
- W4285403797 hasConcept C95457728 @default.
- W4285403797 hasConcept C97541855 @default.
- W4285403797 hasConcept C98045186 @default.
- W4285403797 hasConceptScore W4285403797C111919701 @default.
- W4285403797 hasConceptScore W4285403797C121955636 @default.
- W4285403797 hasConceptScore W4285403797C126255220 @default.
- W4285403797 hasConceptScore W4285403797C154945302 @default.
- W4285403797 hasConceptScore W4285403797C162324750 @default.
- W4285403797 hasConceptScore W4285403797C166957645 @default.
- W4285403797 hasConceptScore W4285403797C196083921 @default.
- W4285403797 hasConceptScore W4285403797C33923547 @default.
- W4285403797 hasConceptScore W4285403797C41008148 @default.
- W4285403797 hasConceptScore W4285403797C79581498 @default.
- W4285403797 hasConceptScore W4285403797C95457728 @default.
- W4285403797 hasConceptScore W4285403797C97541855 @default.
- W4285403797 hasConceptScore W4285403797C98045186 @default.
- W4285403797 hasLocation W42854037971 @default.
- W4285403797 hasOpenAccess W4285403797 @default.
- W4285403797 hasPrimaryLocation W42854037971 @default.
- W4285403797 hasRelatedWork W2093683727 @default.
- W4285403797 hasRelatedWork W2923653485 @default.
- W4285403797 hasRelatedWork W2957776456 @default.
- W4285403797 hasRelatedWork W3088315509 @default.
- W4285403797 hasRelatedWork W3209094908 @default.
- W4285403797 hasRelatedWork W4210912933 @default.
- W4285403797 hasRelatedWork W4255994452 @default.
- W4285403797 hasRelatedWork W4361026739 @default.
- W4285403797 hasRelatedWork W4372194388 @default.
- W4285403797 hasRelatedWork W4379471189 @default.
- W4285403797 hasVolume "311" @default.
- W4285403797 isParatext "false" @default.
- W4285403797 isRetracted "false" @default.
- W4285403797 workType "article" @default.