Matches in SemOpenAlex for { <https://semopenalex.org/work/W3183152661> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3183152661 abstract "Modeling controllable aspects of the environment enable better prioritization of interventions and has become a popular exploration strategy in reinforcement learning methods. Despite repeatedly achieving State-of-the-Art results, this approach has only been studied as a proxy to a reward-based task and has not yet been evaluated on its own. We show that solutions relying on action prediction fail to model important events. Humans, on the other hand, assign blame to their actions to decide what they controlled. Here we propose Controlled Effect Network (CEN), an unsupervised method based on counterfactual measures of blame. CEN is evaluated in a wide range of environments showing that it can identify controlled effects better than popular models based on action prediction." @default.
- W3183152661 created "2021-08-02" @default.
- W3183152661 creator A5038506987 @default.
- W3183152661 creator A5056574222 @default.
- W3183152661 date "2021-06-13" @default.
- W3183152661 modified "2023-10-18" @default.
- W3183152661 title "Did I do that? Blame as a means to identify controlled effects in reinforcement learning." @default.
- W3183152661 hasPublicationYear "2021" @default.
- W3183152661 type Work @default.
- W3183152661 sameAs 3183152661 @default.
- W3183152661 citedByCount "0" @default.
- W3183152661 crossrefType "proceedings-article" @default.
- W3183152661 hasAuthorship W3183152661A5038506987 @default.
- W3183152661 hasAuthorship W3183152661A5056574222 @default.
- W3183152661 hasConcept C108650721 @default.
- W3183152661 hasConcept C119857082 @default.
- W3183152661 hasConcept C121332964 @default.
- W3183152661 hasConcept C127413603 @default.
- W3183152661 hasConcept C154945302 @default.
- W3183152661 hasConcept C15744967 @default.
- W3183152661 hasConcept C180747234 @default.
- W3183152661 hasConcept C201995342 @default.
- W3183152661 hasConcept C2777615720 @default.
- W3183152661 hasConcept C2780148112 @default.
- W3183152661 hasConcept C2780451532 @default.
- W3183152661 hasConcept C2780791683 @default.
- W3183152661 hasConcept C2781466463 @default.
- W3183152661 hasConcept C41008148 @default.
- W3183152661 hasConcept C539667460 @default.
- W3183152661 hasConcept C62520636 @default.
- W3183152661 hasConcept C77805123 @default.
- W3183152661 hasConcept C97541855 @default.
- W3183152661 hasConceptScore W3183152661C108650721 @default.
- W3183152661 hasConceptScore W3183152661C119857082 @default.
- W3183152661 hasConceptScore W3183152661C121332964 @default.
- W3183152661 hasConceptScore W3183152661C127413603 @default.
- W3183152661 hasConceptScore W3183152661C154945302 @default.
- W3183152661 hasConceptScore W3183152661C15744967 @default.
- W3183152661 hasConceptScore W3183152661C180747234 @default.
- W3183152661 hasConceptScore W3183152661C201995342 @default.
- W3183152661 hasConceptScore W3183152661C2777615720 @default.
- W3183152661 hasConceptScore W3183152661C2780148112 @default.
- W3183152661 hasConceptScore W3183152661C2780451532 @default.
- W3183152661 hasConceptScore W3183152661C2780791683 @default.
- W3183152661 hasConceptScore W3183152661C2781466463 @default.
- W3183152661 hasConceptScore W3183152661C41008148 @default.
- W3183152661 hasConceptScore W3183152661C539667460 @default.
- W3183152661 hasConceptScore W3183152661C62520636 @default.
- W3183152661 hasConceptScore W3183152661C77805123 @default.
- W3183152661 hasConceptScore W3183152661C97541855 @default.
- W3183152661 hasLocation W31831526611 @default.
- W3183152661 hasOpenAccess W3183152661 @default.
- W3183152661 hasPrimaryLocation W31831526611 @default.
- W3183152661 hasRelatedWork W103882264 @default.
- W3183152661 hasRelatedWork W170211126 @default.
- W3183152661 hasRelatedWork W2765447956 @default.
- W3183152661 hasRelatedWork W2946249608 @default.
- W3183152661 hasRelatedWork W2946845352 @default.
- W3183152661 hasRelatedWork W2951896810 @default.
- W3183152661 hasRelatedWork W2953749403 @default.
- W3183152661 hasRelatedWork W2963097362 @default.
- W3183152661 hasRelatedWork W2963646405 @default.
- W3183152661 hasRelatedWork W2963896264 @default.
- W3183152661 hasRelatedWork W2965046886 @default.
- W3183152661 hasRelatedWork W3014028012 @default.
- W3183152661 hasRelatedWork W3103946812 @default.
- W3183152661 hasRelatedWork W3169112020 @default.
- W3183152661 hasRelatedWork W3169857478 @default.
- W3183152661 hasRelatedWork W3171853060 @default.
- W3183152661 hasRelatedWork W3174775401 @default.
- W3183152661 hasRelatedWork W3201286590 @default.
- W3183152661 hasRelatedWork W3209066245 @default.
- W3183152661 hasRelatedWork W2555252800 @default.
- W3183152661 isParatext "false" @default.
- W3183152661 isRetracted "false" @default.
- W3183152661 magId "3183152661" @default.
- W3183152661 workType "article" @default.