Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313444766> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4313444766 abstract "In recent years distributional reinforcement learning has produced many state of the art results. Increasingly sample efficient Distributional algorithms for the discrete action domain have been developed over time that vary primarily in the way they parameterize their approximations of value distributions, and how they quantify the differences between those distributions. In this work we transfer three of the most well-known and successful of those algorithms (QR-DQN, IQN and FQF) to the continuous action domain by extending two powerful actor-critic algorithms (TD3 and SAC) with distributional critics. We investigate whether the relative performance of the methods for the discrete action space translates to the continuous case. To that end we compare them empirically on the pybullet implementations of a set of continuous control tasks. Our results indicate qualitative invariance regarding the number and placement of distributional atoms in the deterministic, continuous action setting." @default.
- W4313444766 created "2023-01-06" @default.
- W4313444766 creator A5000470711 @default.
- W4313444766 creator A5055464257 @default.
- W4313444766 creator A5084075127 @default.
- W4313444766 creator A5089963670 @default.
- W4313444766 date "2022-12-29" @default.
- W4313444766 modified "2023-10-18" @default.
- W4313444766 title "Invariance to Quantile Selection in Distributional Continuous Control" @default.
- W4313444766 doi "https://doi.org/10.48550/arxiv.2212.14262" @default.
- W4313444766 hasPublicationYear "2022" @default.
- W4313444766 type Work @default.
- W4313444766 citedByCount "0" @default.
- W4313444766 crossrefType "posted-content" @default.
- W4313444766 hasAuthorship W4313444766A5000470711 @default.
- W4313444766 hasAuthorship W4313444766A5055464257 @default.
- W4313444766 hasAuthorship W4313444766A5084075127 @default.
- W4313444766 hasAuthorship W4313444766A5089963670 @default.
- W4313444766 hasBestOaLocation W43134447661 @default.
- W4313444766 hasConcept C105795698 @default.
- W4313444766 hasConcept C118671147 @default.
- W4313444766 hasConcept C121332964 @default.
- W4313444766 hasConcept C126255220 @default.
- W4313444766 hasConcept C134306372 @default.
- W4313444766 hasConcept C149782125 @default.
- W4313444766 hasConcept C154945302 @default.
- W4313444766 hasConcept C177264268 @default.
- W4313444766 hasConcept C185592680 @default.
- W4313444766 hasConcept C198531522 @default.
- W4313444766 hasConcept C199360897 @default.
- W4313444766 hasConcept C2775924081 @default.
- W4313444766 hasConcept C2780791683 @default.
- W4313444766 hasConcept C33923547 @default.
- W4313444766 hasConcept C36503486 @default.
- W4313444766 hasConcept C41008148 @default.
- W4313444766 hasConcept C43617362 @default.
- W4313444766 hasConcept C62520636 @default.
- W4313444766 hasConcept C72434380 @default.
- W4313444766 hasConcept C81917197 @default.
- W4313444766 hasConcept C97541855 @default.
- W4313444766 hasConceptScore W4313444766C105795698 @default.
- W4313444766 hasConceptScore W4313444766C118671147 @default.
- W4313444766 hasConceptScore W4313444766C121332964 @default.
- W4313444766 hasConceptScore W4313444766C126255220 @default.
- W4313444766 hasConceptScore W4313444766C134306372 @default.
- W4313444766 hasConceptScore W4313444766C149782125 @default.
- W4313444766 hasConceptScore W4313444766C154945302 @default.
- W4313444766 hasConceptScore W4313444766C177264268 @default.
- W4313444766 hasConceptScore W4313444766C185592680 @default.
- W4313444766 hasConceptScore W4313444766C198531522 @default.
- W4313444766 hasConceptScore W4313444766C199360897 @default.
- W4313444766 hasConceptScore W4313444766C2775924081 @default.
- W4313444766 hasConceptScore W4313444766C2780791683 @default.
- W4313444766 hasConceptScore W4313444766C33923547 @default.
- W4313444766 hasConceptScore W4313444766C36503486 @default.
- W4313444766 hasConceptScore W4313444766C41008148 @default.
- W4313444766 hasConceptScore W4313444766C43617362 @default.
- W4313444766 hasConceptScore W4313444766C62520636 @default.
- W4313444766 hasConceptScore W4313444766C72434380 @default.
- W4313444766 hasConceptScore W4313444766C81917197 @default.
- W4313444766 hasConceptScore W4313444766C97541855 @default.
- W4313444766 hasLocation W43134447661 @default.
- W4313444766 hasOpenAccess W4313444766 @default.
- W4313444766 hasPrimaryLocation W43134447661 @default.
- W4313444766 hasRelatedWork W1971600963 @default.
- W4313444766 hasRelatedWork W2095855481 @default.
- W4313444766 hasRelatedWork W2099238421 @default.
- W4313444766 hasRelatedWork W2377946372 @default.
- W4313444766 hasRelatedWork W2803308811 @default.
- W4313444766 hasRelatedWork W2962878825 @default.
- W4313444766 hasRelatedWork W3134128261 @default.
- W4313444766 hasRelatedWork W3167355872 @default.
- W4313444766 hasRelatedWork W3170446423 @default.
- W4313444766 hasRelatedWork W36691172 @default.
- W4313444766 isParatext "false" @default.
- W4313444766 isRetracted "false" @default.
- W4313444766 workType "article" @default.