Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208952172> ?p ?o ?g. }
- W3208952172 abstract "Bias correction techniques are used by most of the high-performing methods for off-policy reinforcement learning. However, these techniques rely on a pre-defined bias correction policy that is either not flexible enough or requires environment-specific tuning of hyperparameters. In this work, we present a simple data-driven approach for guiding bias correction. We demonstrate its effectiveness on the Truncated Quantile Critics -- a state-of-the-art continuous control algorithm. The proposed technique can adjust the bias correction across environments automatically. As a result, it eliminates the need for an extensive hyperparameter search, significantly reducing the actual number of interactions and computation." @default.
- W3208952172 created "2021-11-08" @default.
- W3208952172 creator A5008914065 @default.
- W3208952172 creator A5028940329 @default.
- W3208952172 creator A5039307457 @default.
- W3208952172 creator A5081684657 @default.
- W3208952172 creator A5085388411 @default.
- W3208952172 date "2021-10-26" @default.
- W3208952172 modified "2023-09-27" @default.
- W3208952172 title "Automating Control of Overestimation Bias for Continuous Reinforcement Learning" @default.
- W3208952172 cites W2121863487 @default.
- W3208952172 cites W2123447947 @default.
- W3208952172 cites W2144744117 @default.
- W3208952172 cites W2155968351 @default.
- W3208952172 cites W2158782408 @default.
- W3208952172 cites W2165150801 @default.
- W3208952172 cites W2596758708 @default.
- W3208952172 cites W2740912559 @default.
- W3208952172 cites W2904246096 @default.
- W3208952172 cites W2962878825 @default.
- W3208952172 cites W2962902376 @default.
- W3208952172 cites W2963423916 @default.
- W3208952172 cites W2963704132 @default.
- W3208952172 cites W2963757175 @default.
- W3208952172 cites W2963923407 @default.
- W3208952172 cites W2964121744 @default.
- W3208952172 cites W2995509794 @default.
- W3208952172 cites W3000642679 @default.
- W3208952172 cites W3015082424 @default.
- W3208952172 cites W3034379033 @default.
- W3208952172 cites W3034440351 @default.
- W3208952172 cites W3036162308 @default.
- W3208952172 cites W3114551027 @default.
- W3208952172 cites W3170872007 @default.
- W3208952172 cites W3203189308 @default.
- W3208952172 cites W3204911585 @default.
- W3208952172 cites W3214469502 @default.
- W3208952172 cites W51508254 @default.
- W3208952172 hasPublicationYear "2021" @default.
- W3208952172 type Work @default.
- W3208952172 sameAs 3208952172 @default.
- W3208952172 citedByCount "0" @default.
- W3208952172 crossrefType "posted-content" @default.
- W3208952172 hasAuthorship W3208952172A5008914065 @default.
- W3208952172 hasAuthorship W3208952172A5028940329 @default.
- W3208952172 hasAuthorship W3208952172A5039307457 @default.
- W3208952172 hasAuthorship W3208952172A5081684657 @default.
- W3208952172 hasAuthorship W3208952172A5085388411 @default.
- W3208952172 hasConcept C105795698 @default.
- W3208952172 hasConcept C111472728 @default.
- W3208952172 hasConcept C11413529 @default.
- W3208952172 hasConcept C118671147 @default.
- W3208952172 hasConcept C119857082 @default.
- W3208952172 hasConcept C138885662 @default.
- W3208952172 hasConcept C154945302 @default.
- W3208952172 hasConcept C2775924081 @default.
- W3208952172 hasConcept C2780586882 @default.
- W3208952172 hasConcept C33923547 @default.
- W3208952172 hasConcept C41008148 @default.
- W3208952172 hasConcept C45374587 @default.
- W3208952172 hasConcept C8642999 @default.
- W3208952172 hasConcept C97541855 @default.
- W3208952172 hasConceptScore W3208952172C105795698 @default.
- W3208952172 hasConceptScore W3208952172C111472728 @default.
- W3208952172 hasConceptScore W3208952172C11413529 @default.
- W3208952172 hasConceptScore W3208952172C118671147 @default.
- W3208952172 hasConceptScore W3208952172C119857082 @default.
- W3208952172 hasConceptScore W3208952172C138885662 @default.
- W3208952172 hasConceptScore W3208952172C154945302 @default.
- W3208952172 hasConceptScore W3208952172C2775924081 @default.
- W3208952172 hasConceptScore W3208952172C2780586882 @default.
- W3208952172 hasConceptScore W3208952172C33923547 @default.
- W3208952172 hasConceptScore W3208952172C41008148 @default.
- W3208952172 hasConceptScore W3208952172C45374587 @default.
- W3208952172 hasConceptScore W3208952172C8642999 @default.
- W3208952172 hasConceptScore W3208952172C97541855 @default.
- W3208952172 hasLocation W32089521721 @default.
- W3208952172 hasOpenAccess W3208952172 @default.
- W3208952172 hasPrimaryLocation W32089521721 @default.
- W3208952172 hasRelatedWork W1599193893 @default.
- W3208952172 hasRelatedWork W2592857946 @default.
- W3208952172 hasRelatedWork W2808982242 @default.
- W3208952172 hasRelatedWork W2890583230 @default.
- W3208952172 hasRelatedWork W2912851808 @default.
- W3208952172 hasRelatedWork W2949488369 @default.
- W3208952172 hasRelatedWork W2952295663 @default.
- W3208952172 hasRelatedWork W2989857936 @default.
- W3208952172 hasRelatedWork W2990095073 @default.
- W3208952172 hasRelatedWork W2994651240 @default.
- W3208952172 hasRelatedWork W3005871659 @default.
- W3208952172 hasRelatedWork W3014057631 @default.
- W3208952172 hasRelatedWork W3035825996 @default.
- W3208952172 hasRelatedWork W3036771316 @default.
- W3208952172 hasRelatedWork W3043270561 @default.
- W3208952172 hasRelatedWork W3120339597 @default.
- W3208952172 hasRelatedWork W3136455557 @default.
- W3208952172 hasRelatedWork W3158206273 @default.
- W3208952172 hasRelatedWork W3167940580 @default.
- W3208952172 hasRelatedWork W3172590413 @default.
- W3208952172 isParatext "false" @default.