Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382239320> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4382239320 endingPage "7413" @default.
- W4382239320 startingPage "7405" @default.
- W4382239320 abstract "We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs). Both the reward functions and the state transition kernels are unknown and allowed to vary arbitrarily over time with a budget on their cumulative variations. When this variation budget is known a prior, we propose two restart-based algorithms, namely Restart-RSMB and Restart-RSQ, and establish their dynamic regrets. Based on these results, we further present a meta-algorithm that does not require any prior knowledge of the variation budget and can adaptively detect the non-stationarity on the exponential value functions. A dynamic regret lower bound is then established for non-stationary risk-sensitive RL to certify the near-optimality of the proposed algorithms. Our results also show that the risk control and the handling of the non-stationarity can be separately designed in the algorithm if the variation budget is known a prior, while the non-stationary detection mechanism in the adaptive algorithm depends on the risk parameter. This work offers the first non-asymptotic theoretical analyses for the non-stationary risk-sensitive RL in the literature." @default.
- W4382239320 created "2023-06-28" @default.
- W4382239320 creator A5027576572 @default.
- W4382239320 creator A5042580848 @default.
- W4382239320 creator A5060421840 @default.
- W4382239320 date "2023-06-26" @default.
- W4382239320 modified "2023-09-23" @default.
- W4382239320 title "Non-stationary Risk-Sensitive Reinforcement Learning: Near-Optimal Dynamic Regret, Adaptive Detection, and Separation Design" @default.
- W4382239320 doi "https://doi.org/10.1609/aaai.v37i6.25901" @default.
- W4382239320 hasPublicationYear "2023" @default.
- W4382239320 type Work @default.
- W4382239320 citedByCount "0" @default.
- W4382239320 crossrefType "journal-article" @default.
- W4382239320 hasAuthorship W4382239320A5027576572 @default.
- W4382239320 hasAuthorship W4382239320A5042580848 @default.
- W4382239320 hasAuthorship W4382239320A5060421840 @default.
- W4382239320 hasBestOaLocation W43822393201 @default.
- W4382239320 hasConcept C105795698 @default.
- W4382239320 hasConcept C106189395 @default.
- W4382239320 hasConcept C119857082 @default.
- W4382239320 hasConcept C121332964 @default.
- W4382239320 hasConcept C126255220 @default.
- W4382239320 hasConcept C133710760 @default.
- W4382239320 hasConcept C134306372 @default.
- W4382239320 hasConcept C151376022 @default.
- W4382239320 hasConcept C154945302 @default.
- W4382239320 hasConcept C159886148 @default.
- W4382239320 hasConcept C2778334786 @default.
- W4382239320 hasConcept C31972630 @default.
- W4382239320 hasConcept C33923547 @default.
- W4382239320 hasConcept C41008148 @default.
- W4382239320 hasConcept C44870925 @default.
- W4382239320 hasConcept C50817715 @default.
- W4382239320 hasConcept C97541855 @default.
- W4382239320 hasConcept C98763669 @default.
- W4382239320 hasConceptScore W4382239320C105795698 @default.
- W4382239320 hasConceptScore W4382239320C106189395 @default.
- W4382239320 hasConceptScore W4382239320C119857082 @default.
- W4382239320 hasConceptScore W4382239320C121332964 @default.
- W4382239320 hasConceptScore W4382239320C126255220 @default.
- W4382239320 hasConceptScore W4382239320C133710760 @default.
- W4382239320 hasConceptScore W4382239320C134306372 @default.
- W4382239320 hasConceptScore W4382239320C151376022 @default.
- W4382239320 hasConceptScore W4382239320C154945302 @default.
- W4382239320 hasConceptScore W4382239320C159886148 @default.
- W4382239320 hasConceptScore W4382239320C2778334786 @default.
- W4382239320 hasConceptScore W4382239320C31972630 @default.
- W4382239320 hasConceptScore W4382239320C33923547 @default.
- W4382239320 hasConceptScore W4382239320C41008148 @default.
- W4382239320 hasConceptScore W4382239320C44870925 @default.
- W4382239320 hasConceptScore W4382239320C50817715 @default.
- W4382239320 hasConceptScore W4382239320C97541855 @default.
- W4382239320 hasConceptScore W4382239320C98763669 @default.
- W4382239320 hasIssue "6" @default.
- W4382239320 hasLocation W43822393201 @default.
- W4382239320 hasOpenAccess W4382239320 @default.
- W4382239320 hasPrimaryLocation W43822393201 @default.
- W4382239320 hasRelatedWork W2124144580 @default.
- W4382239320 hasRelatedWork W2149943599 @default.
- W4382239320 hasRelatedWork W2952099252 @default.
- W4382239320 hasRelatedWork W3092949629 @default.
- W4382239320 hasRelatedWork W3140738360 @default.
- W4382239320 hasRelatedWork W3167472281 @default.
- W4382239320 hasRelatedWork W3198596521 @default.
- W4382239320 hasRelatedWork W4302063494 @default.
- W4382239320 hasRelatedWork W4302357557 @default.
- W4382239320 hasRelatedWork W4309799095 @default.
- W4382239320 hasVolume "37" @default.
- W4382239320 isParatext "false" @default.
- W4382239320 isRetracted "false" @default.
- W4382239320 workType "article" @default.